category stringclasses 19
values | ctf_task_type stringclasses 7
values | dataset stringclasses 1
value | id stringlengths 29 29 | messages listlengths 3 3 | metadata unknown | source_dataset stringclasses 3
values | source_path stringlengths 0 93 | split stringclasses 1
value | type stringclasses 1
value |
|---|---|---|---|---|---|---|---|---|---|
ai | ai | ctf-dataset | ctf-lora-032284114fa34d4f0493 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「教程：构建朴素的 Agent Loop」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"... | {
"category": "ai",
"chars": 259,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "教程：构建朴素的 Agent Loop",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop"
],
"original_id": "docs-f3d22932f04d4d99ea1b",
"original_line": 14,
"original_split": "train",
"... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-0429febf1ac66032734b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「4. Context Design」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"co... | {
"category": "ai",
"chars": 3962,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "4. Context Design",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"4. Context Design"
],
"original_id": "docs-ef7820052e5c774cda64",
"original_line": 18,
"origi... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-051b5fcc9393a1477adf | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/history.md` 中的章节「「现代」CTF 竞赛」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introducti... | {
"category": "introduction",
"chars": 235,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "「现代」CTF 竞赛",
"heading_path": [
"CTF 历史",
"「现代」CTF 竞赛"
],
"original_id": "docs-f2846898b69929010ee4",
"original_line": 525,
"original_split": "train",
"rec... | docs_distilled_v1 | introduction/history.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-08276c8a61f06931666d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/heap-flags.md` 中的章节「关于Heap flags」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"co... | {
"category": "reverse",
"chars": 2288,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "关于Heap flags",
"heading_path": [
"Heap Flags",
"关于Heap flags"
],
"original_id": "docs-62a506020d628558eb45",
"original_line": 1515,
"original_split": "train",
... | docs_distilled_v1 | reverse/platform/windows/anti-debug/heap-flags.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-091899049d36a17170d2 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/classical/others.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/classica... | {
"category": "crypto",
"chars": 502,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "原理",
"heading_path": [
"其它类型加密",
"列移位加密",
"原理"
],
"original_id": "docs-67fbb0c0bdd184fec902",
"original_line": 370,
"original_split": "train",
"record_type"... | docs_distilled_v1 | crypto/classical/others.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-095c0e3c3e3421a97ee8 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/archive/zip.md` 中的章节「例题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/archive/zip.md`\n... | {
"category": "misc",
"chars": 275,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 22,
"ctf_task_type": "ai",
"heading": "例题",
"heading_path": [
"-- coding: utf-8 --",
"伪加密",
"例题"
],
"original_id": "docs-8f0b461fa116aa4002e4",
"original_line": 553,
"original_split": "train",
"rec... | docs_distilled_v1 | misc/archive/zip.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-0963251b4162f2e6b1d0 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「战争分享模式 - Belluminar」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/intr... | {
"category": "introduction",
"chars": 222,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "战争分享模式 - Belluminar",
"heading_path": [
"CTF 竞赛模式简介",
"战争分享模式 - Belluminar"
],
"original_id": "docs-344d81739983de5ba726",
"original_line": 527,
"original_s... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-0b239adef0a51841cd87 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「8. 实战：利用 Naive Agent Loop 解决简单的 CTF 题目」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "u... | {
"category": "ai",
"chars": 5189,
"chunk_count": 3,
"chunk_index": 1,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "8. 实战：利用 Naive Agent Loop 解决简单的 CTF 题目",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"8. 实战：利用 Naive Agent Loop 解决简单的 CTF 题目"
],
"original_id": "docs-0da8c20c47d7... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-0be080016148864bbb41 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「1. Loop Design」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"conte... | {
"category": "ai",
"chars": 496,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "1. Loop Design",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"1. Loop Design"
],
"original_id": "docs-f11bf10fa220d39d9fcd",
"original_line": 15,
"original_spl... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-106fc65fb639bea2c48d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「2. OpenAI-Compatible Request」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
... | {
"category": "ai",
"chars": 1921,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "2. OpenAI-Compatible Request",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"2. OpenAI-Compatible Request"
],
"original_id": "docs-2a13d81e2d9a274a2865",
"origin... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-13291dae4ca0fad27e37 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/archive/zip.md` 中的章节「-- coding: utf-8 --」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/... | {
"category": "misc",
"chars": 421,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "-- coding: utf-8 --",
"heading_path": [
"-- coding: utf-8 --"
],
"original_id": "docs-177130262174527a257f",
"original_line": 548,
"original_split": "train",
"record_... | docs_distilled_v1 | misc/archive/zip.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-13984c6dd66c6a092e8b | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/tools/constraint/z3.md` 中的章节「添加约束」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/t... | {
"category": "reverse",
"chars": 301,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "添加约束",
"heading_path": [
"z3",
"基本用法",
"添加约束"
],
"original_id": "docs-c7d8c2271cb032264ce8",
"original_line": 1554,
"original_split": "train",
"record_type... | docs_distilled_v1 | reverse/tools/constraint/z3.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-14758b911841ce129f88 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/introduction.md` 中的章节「fopen」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`... | {
"category": "pwn",
"chars": 1086,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "fopen",
"heading_path": [
"else",
"fopen"
],
"original_id": "docs-ce9659f4d64a08a38dc4",
"original_line": 1211,
"original_split": "train",
"record_type": "doc_sec... | docs_distilled_v1 | pwn/linux/user-mode/io-file/introduction.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-18741c76d845926df088 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/experience.md` 中的章节「关注 Gamebox 状态」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/intr... | {
"category": "introduction",
"chars": 599,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "关注 Gamebox 状态",
"heading_path": [
"线下攻防经验小结",
"关注 Gamebox 状态"
],
"original_id": "docs-4fd6307364334db63f6e",
"original_line": 521,
"original_split": "train"... | docs_distilled_v1 | introduction/experience.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-1c23198ee0aa534e5198 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/fake-vtable-exploit.md` 中的章节「思路：」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": ... | {
"category": "pwn",
"chars": 3074,
"chunk_count": 2,
"chunk_index": 1,
"ctf_score": 22,
"ctf_task_type": "ai",
"heading": "思路：",
"heading_path": [
"伪造vtable劫持程序流程",
"2018 HCTF the_end",
"思路："
],
"original_id": "docs-679f90517831c111372c",
"original_line": 1203,
"original_split": "tr... | docs_distilled_v1 | pwn/linux/user-mode/io-file/fake-vtable-exploit.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-1cf89e6f1801375dc39c | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/basic/introduction.md` 中的章节「代数系统和近世代数」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto... | {
"category": "crypto",
"chars": 390,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "代数系统和近世代数",
"heading_path": [
"基础数学知识",
"代数系统和近世代数"
],
"original_id": "docs-cfc559fbb9bdbc1efb88",
"original_line": 14,
"original_split": "validation",
"record_... | docs_distilled_v1 | crypto/basic/introduction.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-1d60d2710a28f14dab2f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/obfuscate/smc.md` 中的章节「例题：GWCTF 2019 - re3」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/... | {
"category": "reverse",
"chars": 3915,
"chunk_count": 3,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "例题：GWCTF 2019 - re3",
"heading_path": [
"Self-Modified Code",
"例题：GWCTF 2019 - re3"
],
"original_id": "docs-45dc8608f42489313f65",
"original_line": 1485,
"origi... | docs_distilled_v1 | reverse/obfuscate/smc.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-1e2e663bd7e7f26270cd | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/asymmetric/knapsack/knapsack.md` 中的章节「背包问题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/c... | {
"category": "crypto",
"chars": 694,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "背包问题",
"heading_path": [
"背包加密",
"背包问题"
],
"original_id": "docs-dcba0dacf775863bb46e",
"original_line": 215,
"original_split": "train",
"record_type": "doc_sect... | docs_distilled_v1 | crypto/asymmetric/knapsack/knapsack.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-1ed6902780b4ba0bbdbf | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/certificate/introduction.md` 中的章节「PEM」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto... | {
"category": "crypto",
"chars": 380,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "PEM",
"heading_path": [
"证书格式",
"PEM"
],
"original_id": "docs-8db02b2a88ee27511e36",
"original_line": 20,
"original_split": "validation",
"record_type": "doc_se... | docs_distilled_v1 | crypto/certificate/introduction.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-1f1c957af0354d317eea | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/tools/constraint/z3.md` 中的章节「约束求解」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/t... | {
"category": "reverse",
"chars": 435,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "约束求解",
"heading_path": [
"z3",
"基本用法",
"约束求解"
],
"original_id": "docs-6017f47f0684521d2921",
"original_line": 1555,
"original_split": "train",
"record_type... | docs_distilled_v1 | reverse/tools/constraint/z3.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-1f1f7c765937e9217b07 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/identify-encode-encryption/introduction.md` 中的章节「MD5」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": ... | {
"category": "reverse",
"chars": 2343,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "MD5",
"heading_path": [
"常见加密算法和编码识别",
"MD5"
],
"original_id": "docs-4f61f59908373049e08c",
"original_line": 1476,
"original_split": "train",
"record_type": "... | docs_distilled_v1 | reverse/identify-encode-encryption/introduction.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-1fa52b3f733208732f3e | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/introduction.md` 中的章节「FILE介绍」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：... | {
"category": "pwn",
"chars": 1661,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "FILE介绍",
"heading_path": [
"FILE结构",
"FILE介绍"
],
"original_id": "docs-a63b4f6b1bb0f4770ca4",
"original_line": 1207,
"original_split": "train",
"record_type": "doc... | docs_distilled_v1 | pwn/linux/user-mode/io-file/introduction.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-1fb23a346b6867017128 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「计分规则」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduction/mode.m... | {
"category": "introduction",
"chars": 314,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "计分规则",
"heading_path": [
"CTF 竞赛模式简介",
"战争分享模式 - Belluminar",
"计分规则"
],
"original_id": "docs-4bb7b40eaae5aaf6ddd1",
"original_line": 530,
"original_spli... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-216eaeef1ab659b3d209 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/race-condition/problem.md` 中的章节「基本思路」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：... | {
"category": "pwn",
"chars": 551,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 24,
"ctf_task_type": "ai",
"heading": "基本思路",
"heading_path": [
"题目",
"构造例子",
"基本思路"
],
"original_id": "docs-459562be8c397164b50d",
"original_line": 1229,
"original_split": "train",
"record_type": "... | docs_distilled_v1 | pwn/linux/user-mode/race-condition/problem.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-255cbcf5f1dd52188515 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/obfuscate/junk-code.md` 中的章节「求解」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/obf... | {
"category": "reverse",
"chars": 218,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "求解",
"heading_path": [
"花指令",
"例题：N1CTF2020 - oflo",
"求解"
],
"original_id": "docs-2ded7a3508ca39e68bc7",
"original_line": 1482,
"original_split": "train",
... | docs_distilled_v1 | reverse/obfuscate/junk-code.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-26b0e54e14ef1c6c35f1 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/intro.md` 中的章节「8. 实战：利用 Naive Agent Loop 解决简单的 CTF 题目」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "u... | {
"category": "ai",
"chars": 4811,
"chunk_count": 3,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "8. 实战：利用 Naive Agent Loop 解决简单的 CTF 题目",
"heading_path": [
"简介",
"教程：构建朴素的 Agent Loop",
"8. 实战：利用 Naive Agent Loop 解决简单的 CTF 题目"
],
"original_id": "docs-9b8fe79d5a34... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/intro.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-281cfe47b7e0b028febf | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/ntglobalflag.md` 中的章节「如何绕过检测?」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"conte... | {
"category": "reverse",
"chars": 208,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "如何绕过检测?",
"heading_path": [
"NtGlobalFlag",
"如何绕过检测?"
],
"original_id": "docs-ec78503dfc40f89be22a",
"original_line": 1525,
"original_split": "train",
"record_... | docs_distilled_v1 | reverse/platform/windows/anti-debug/ntglobalflag.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-2be91e3983b4d75abfab | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/picture/png.md` 中的章节「IEND」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/picture/png.md`... | {
"category": "misc",
"chars": 195,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "IEND",
"heading_path": [
"PNG",
"文件格式",
"IEND"
],
"original_id": "docs-36d518f773f3d3c71d01",
"original_line": 31,
"original_split": "validation",
"record_typ... | docs_distilled_v1 | misc/picture/png.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-320f56f8a3d20c47534d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/windows/anti-debug/heap-flags.md` 中的章节「检测Flags字段」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"conte... | {
"category": "reverse",
"chars": 1962,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "检测Flags字段",
"heading_path": [
"Heap Flags",
"检测Flags字段"
],
"original_id": "docs-80aaf818407372bc0814",
"original_line": 1517,
"original_split": "train",
"reco... | docs_distilled_v1 | reverse/platform/windows/anti-debug/heap-flags.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-3382d5b8e6b41bea07ac | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/introduction.md` 中的章节「简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/ai/introduction.md`\n标题... | {
"category": "ai",
"chars": 898,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 20,
"ctf_task_type": "ai",
"heading": "简介",
"heading_path": [
"Artificial Intelligence",
"简介"
],
"original_id": "docs-7cb17126dc423baf47fc",
"original_line": 1,
"original_split": "train",
"record_type": ... | docs_distilled_v1 | ai/introduction.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-36183e6c5bf146c83058 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/obfuscate/smc.md` 中的章节「例题：GWCTF 2019 - re3」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/... | {
"category": "reverse",
"chars": 2139,
"chunk_count": 3,
"chunk_index": 2,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "例题：GWCTF 2019 - re3",
"heading_path": [
"Self-Modified Code",
"例题：GWCTF 2019 - re3"
],
"original_id": "docs-fc06bd7b252b7d0c1af0",
"original_line": 1487,
"origi... | docs_distilled_v1 | reverse/obfuscate/smc.md | train | ctf_lora_sft |
blockchain | ai | ctf-dataset | ctf-lora-378beed55c4bb1f046af | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/publicblockchain/weaknesses.md` 中的章节「Finney attack」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "blockchain",
"chars": 339,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "Finney attack",
"heading_path": [
"Blockchain Weaknesses",
"Double-spending attack",
"Finney attack"
],
"original_id": "docs-113d886588b7454f5643",
"origina... | docs_distilled_v1 | blockchain/publicblockchain/weaknesses.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-390f7e8ab172d1c6415e | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/exploitation/tricks/qemu-monitor.md` 中的章节「利用」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"co... | {
"category": "pwn",
"chars": 887,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 22,
"ctf_task_type": "ai",
"heading": "利用",
"heading_path": [
"DO NOT DELETE",
"利用"
],
"original_id": "docs-a96fee44a4f4614545a7",
"original_line": 79,
"original_split": "validation",
"record_type": "do... | docs_distilled_v1 | pwn/virtualization/qemu/exploitation/tricks/qemu-monitor.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-3916776b3c1628068347 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「关于 AI Agent 在 CTF 中的使用边界说明」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
... | {
"category": "ai",
"chars": 336,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "关于 AI Agent 在 CTF 中的使用边界说明",
"heading_path": [
"AI Agent",
"关于 AI Agent 在 CTF 中的使用边界说明"
],
"original_id": "docs-23c5ce8dedd855a565f0",
"original_line": 12,
"original_... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
executable | ai | ctf-dataset | ctf-lora-3c16cd3962ddce9fe45f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/pe/pe-excutable.md` 中的章节「PE 简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/executabl... | {
"category": "executable",
"chars": 963,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "PE 简介",
"heading_path": [
"PE 文件格式",
"PE 简介"
],
"original_id": "docs-fcf0bee56732afde8b23",
"original_line": 490,
"original_split": "train",
"record_type": ... | docs_distilled_v1 | executable/pe/pe-excutable.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-3c83bf539686d08987de | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/race-condition/problem.md` 中的章节「源代码」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`... | {
"category": "pwn",
"chars": 851,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "源代码",
"heading_path": [
"题目",
"构造例子",
"源代码"
],
"original_id": "docs-f1b0bb0b671dbde66995",
"original_line": 1227,
"original_split": "train",
"record_type": "do... | docs_distilled_v1 | pwn/linux/user-mode/race-condition/problem.md | train | ctf_lora_sft |
executable | ai | ctf-dataset | ctf-lora-3db18d0788e17ff8c3b0 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/pe/pe-excutable.md` 中的章节「IMAGE_NT_HEADERS」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`doc... | {
"category": "executable",
"chars": 415,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "IMAGE_NT_HEADERS",
"heading_path": [
"PE 文件格式",
"PE文件头",
"IMAGE_NT_HEADERS"
],
"original_id": "docs-8159c7b81c7159bcbd6c",
"original_line": 493,
"original... | docs_distilled_v1 | executable/pe/pe-excutable.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-40f3499f5925a33b8ccc | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/platform/linux/ld_preload.md` 中的章节「例题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/rever... | {
"category": "reverse",
"chars": 3283,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "例题",
"heading_path": [
"LD_PRELOAD",
"例题"
],
"original_id": "docs-18320e4a3dbb83cb20fe",
"original_line": 1500,
"original_split": "train",
"record_type": "doc... | docs_distilled_v1 | reverse/platform/linux/ld_preload.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-422e649216fc00efbeca | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/vm/vm.md` 中的章节「注册SEH」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/vm/vm.md`\n标题：... | {
"category": "reverse",
"chars": 2363,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "注册SEH",
"heading_path": [
"虚拟机分析",
"注册SEH"
],
"original_id": "docs-f99e5ba8415e341d8073",
"original_line": 1582,
"original_split": "train",
"record_type": "do... | docs_distilled_v1 | reverse/vm/vm.md | train | ctf_lora_sft |
android | ai | ctf-dataset | ctf-lora-446d64b407097a8906bd | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/android/basic_operating_mechanism/readme.md` 中的章节「Android 应用运行机制简述」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"cont... | {
"category": "android",
"chars": 239,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "Android 应用运行机制简述",
"heading_path": [
"Android 应用运行机制简述"
],
"original_id": "docs-dab5863e884283a3c5bb",
"original_line": 28,
"original_split": "train",
"record_type... | docs_distilled_v1 | android/basic_operating_mechanism/readme.md | train | ctf_lora_sft |
executable | ai | ctf-dataset | ctf-lora-4700e04eb1693f31039c | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/executable/elf/structure/misc-sections.md` 中的章节「ELF 标准」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`d... | {
"category": "executable",
"chars": 599,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "ELF 标准",
"heading_path": [
"Misc Sections",
".gnu.hash",
"ELF 标准"
],
"original_id": "docs-6771786e74d2dc12499b",
"original_line": 482,
"original_split": "... | docs_distilled_v1 | executable/elf/structure/misc-sections.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-4f55d8cf1b0af9919747 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/classical/polyalphabetic.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/... | {
"category": "crypto",
"chars": 685,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "原理",
"heading_path": [
"多表代换加密",
"Playfair",
"原理"
],
"original_id": "docs-77be02c4403168f73202",
"original_line": 19,
"original_split": "test",
"record_type... | docs_distilled_v1 | crypto/classical/polyalphabetic.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-5022a0daf88f0d85805f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/obfuscate/junk-code.md` 中的章节「逆向分析」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/o... | {
"category": "reverse",
"chars": 5038,
"chunk_count": 3,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "逆向分析",
"heading_path": [
"花指令",
"例题：N1CTF2020 - oflo",
"逆向分析"
],
"original_id": "docs-214710232e290f992282",
"original_line": 1480,
"original_split": "train... | docs_distilled_v1 | reverse/obfuscate/junk-code.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-515b96b92c00a94300d0 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「出题阶段」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduction/mode.m... | {
"category": "introduction",
"chars": 420,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "出题阶段",
"heading_path": [
"CTF 竞赛模式简介",
"战争分享模式 - Belluminar",
"出题阶段"
],
"original_id": "docs-dc1e07a0f116f280d3f0",
"original_line": 529,
"original_spli... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-523120b1c6a6a8b25dab | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/archive/zip.md` 中的章节「参考文献」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/archive/zip.md`... | {
"category": "misc",
"chars": 225,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "参考文献",
"heading_path": [
"-- coding: utf-8 --",
"参考文献"
],
"original_id": "docs-ea8b84a370e26d55f971",
"original_line": 554,
"original_split": "train",
"record_typ... | docs_distilled_v1 | misc/archive/zip.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-53620d8da567371fc879 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/blockcipher/des.md` 中的章节「2019 CISCN part_des」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs... | {
"category": "crypto",
"chars": 1808,
"chunk_count": 3,
"chunk_index": 2,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "2019 CISCN part_des",
"heading_path": [
"-- coding: utf-8 --",
"2019 CISCN part_des"
],
"original_id": "docs-1ba90d302df9d1600b35",
"original_line": 18,
"origina... | docs_distilled_v1 | crypto/blockcipher/des.md | train | ctf_lora_sft |
blockchain | ai | ctf-dataset | ctf-lora-53f4a228fab95f73880e | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/publicblockchain/weaknesses.md` 中的章节「Double-spending attack」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"... | {
"category": "blockchain",
"chars": 297,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "Double-spending attack",
"heading_path": [
"Blockchain Weaknesses",
"Double-spending attack"
],
"original_id": "docs-d12e20d9bcc7ff402cae",
"original_line": 189... | docs_distilled_v1 | blockchain/publicblockchain/weaknesses.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-544112800c6362b42277 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/traffic/fix.md` 中的章节「例题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/traffic/fix.md`\n... | {
"category": "misc",
"chars": 2191,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "例题",
"heading_path": [
"PCAP 文件修复",
"例题"
],
"original_id": "docs-dc0ef00e1bb22a226751",
"original_line": 600,
"original_split": "train",
"record_type": "doc_sect... | docs_distilled_v1 | misc/traffic/fix.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-547cbb41ae7cae51377d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/traffic/introduction.md` 中的章节「流量包分析简介」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/tra... | {
"category": "misc",
"chars": 346,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "流量包分析简介",
"heading_path": [
"流量包分析简介"
],
"original_id": "docs-998c0e19a17ebdfc9325",
"original_line": 601,
"original_split": "train",
"record_type": "doc_section_dist... | docs_distilled_v1 | misc/traffic/introduction.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-5494e208123acc4dc110 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/agent-loop/patterns/react.md` 中的章节「ReAct」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"conte... | {
"category": "ai",
"chars": 236,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "ReAct",
"heading_path": [
"ReAct"
],
"original_id": "docs-3112bdeb7c47582bc5d3",
"original_line": 23,
"original_split": "train",
"record_type": "doc_section_distillatio... | docs_distilled_v1 | ai/ai-for-security/agent/agent-loop/patterns/react.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-54cfff4324a3f9dc0a02 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/qemu/basic-knowledge/mm.md` 中的章节「REFERENCE」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "pwn",
"chars": 567,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "REFERENCE",
"heading_path": [
"QEMU 内存管理",
"REFERENCE"
],
"original_id": "docs-6e21e012404a4727a9c4",
"original_line": 1428,
"original_split": "train",
"record_typ... | docs_distilled_v1 | pwn/virtualization/qemu/basic-knowledge/mm.md | train | ctf_lora_sft |
reverse | ai | ctf-dataset | ctf-lora-55aa3eeb5718319b82c1 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/reverse/vm/vm.md` 中的章节「恢复堆栈平衡」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/reverse/vm/vm.md`\n标题... | {
"category": "reverse",
"chars": 1304,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "恢复堆栈平衡",
"heading_path": [
"虚拟机分析",
"恢复堆栈平衡"
],
"original_id": "docs-580a8ddf807c98888c2d",
"original_line": 1583,
"original_split": "train",
"record_type": "... | docs_distilled_v1 | reverse/vm/vm.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-55b4e3f2f80b921c11b0 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/traffic/protocols/usb.md` 中的章节「参考文献」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/traff... | {
"category": "misc",
"chars": 532,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "参考文献",
"heading_path": [
"keep a list of the N best things we have seen, discard anything else",
"参考文献"
],
"original_id": "docs-06c8a51ac18e9bdcd918",
"original_line"... | docs_distilled_v1 | misc/traffic/protocols/usb.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-5641b7a60131fb5b85ed | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「What's next...?」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content"... | {
"category": "ai",
"chars": 1593,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "What's next...?",
"heading_path": [
"AI Agent",
"What's next...?"
],
"original_id": "docs-83c58c25d6caa54329c9",
"original_line": 11,
"original_split": "train",
"r... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-58ef9a59a1b59ef1aeda | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/basic-knowledge/io-virtualization.md` 中的章节「VirtQueue：传输层抽象」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
... | {
"category": "pwn",
"chars": 848,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "VirtQueue：传输层抽象",
"heading_path": [
"IO 虚拟化",
"软件半虚拟化 - virtio",
"VirtQueue：传输层抽象"
],
"original_id": "docs-96810b711628c353c73b",
"original_line": 1411,
"origina... | docs_distilled_v1 | pwn/virtualization/basic-knowledge/io-virtualization.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-58fce1adcc285af74cda | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/disk-memory/problem.md` 中的章节「2018 网鼎杯第一场 clip」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/... | {
"category": "misc",
"chars": 1106,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "2018 网鼎杯第一场 clip",
"heading_path": [
"题目",
"2018 网鼎杯第一场 clip"
],
"original_id": "docs-721bbc4318b15c12b612",
"original_line": 559,
"original_split": "train",
"re... | docs_distilled_v1 | misc/disk-memory/problem.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-59e1e487614da493c87f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/mode.md` 中的章节「赛制介绍」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introduction/mode.m... | {
"category": "introduction",
"chars": 530,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "赛制介绍",
"heading_path": [
"CTF 竞赛模式简介",
"战争分享模式 - Belluminar",
"赛制介绍"
],
"original_id": "docs-8b5b09ecbb02c265e661",
"original_line": 528,
"original_spli... | docs_distilled_v1 | introduction/mode.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-5f1991e1303747bd5a2f | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/virtualization/basic-knowledge/cpu-virtualization.md` 中的章节「CPU 虚拟化」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"... | {
"category": "pwn",
"chars": 713,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "CPU 虚拟化",
"heading_path": [
"CPU 虚拟化"
],
"original_id": "docs-73edb6e5fe1df0f5263a",
"original_line": 1399,
"original_split": "train",
"record_type": "doc_section_dist... | docs_distilled_v1 | pwn/virtualization/basic-knowledge/cpu-virtualization.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-626aa0f1309103df7dee | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/classical/others.md` 中的章节「原理」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/classica... | {
"category": "crypto",
"chars": 255,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "原理",
"heading_path": [
"其它类型加密",
"BrainFuck",
"原理"
],
"original_id": "docs-dbd4ec93838695ecac27",
"original_line": 373,
"original_split": "train",
"record_t... | docs_distilled_v1 | crypto/classical/others.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-631ab920c96674bdc3e0 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/blockcipher/mode/cbc.md` 中的章节「加密」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/crypto/bloc... | {
"category": "crypto",
"chars": 588,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "加密",
"heading_path": [
"CBC",
"加密"
],
"original_id": "docs-b43a1d6ee726f0d24194",
"original_line": 17,
"original_split": "validation",
"record_type": "doc_secti... | docs_distilled_v1 | crypto/blockcipher/mode/cbc.md | train | ctf_lora_sft |
blockchain | ai | ctf-dataset | ctf-lora-640cb76488821d05db6a | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/challenges.md` 中的章节「Blockchain Security Challenges in CTF」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"co... | {
"category": "blockchain",
"chars": 272,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 22,
"ctf_task_type": "ai",
"heading": "Blockchain Security Challenges in CTF",
"heading_path": [
"Blockchain Security Challenges",
"Blockchain Security Challenges in CTF"
],
"original_id": "docs-56bdec... | docs_distilled_v1 | blockchain/challenges.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-6425bffe5160529ce3dd | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/picture/introduction.md` 中的章节「例题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/picture/... | {
"category": "misc",
"chars": 1269,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "例题",
"heading_path": [
"图片分析简介",
"元数据（Metadata）",
"例题"
],
"original_id": "docs-8686db00d615425ee226",
"original_line": 578,
"original_split": "train",
"recor... | docs_distilled_v1 | misc/picture/introduction.md | train | ctf_lora_sft |
ai | ai | ctf-dataset | ctf-lora-648f2d97fe0b75e5905d | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/ai/ai-for-security/agent/introduction.md` 中的章节「AI Agent 的系统架构」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content":... | {
"category": "ai",
"chars": 182,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 14,
"ctf_task_type": "ai",
"heading": "AI Agent 的系统架构",
"heading_path": [
"AI Agent",
"AI Agent 的系统架构"
],
"original_id": "docs-b7ff6db9763851cf7e9c",
"original_line": 3,
"original_split": "train",
"recor... | docs_distilled_v1 | ai/ai-for-security/agent/introduction.md | train | ctf_lora_sft |
pwn | ai | ctf-dataset | ctf-lora-6741356d0e2dc5a5853c | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/pwn/linux/user-mode/io-file/fsop.md` 中的章节「示例」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/pwn/li... | {
"category": "pwn",
"chars": 1734,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "示例",
"heading_path": [
"FSOP",
"示例"
],
"original_id": "docs-094e8c443db7582a4c69",
"original_line": 1206,
"original_split": "train",
"record_type": "doc_section_d... | docs_distilled_v1 | pwn/linux/user-mode/io-file/fsop.md | train | ctf_lora_sft |
misc | ai | ctf-dataset | ctf-lora-68047867a556f41f6a93 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/misc/traffic/protocols/wifi.md` 中的章节「例题」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/misc/traffi... | {
"category": "misc",
"chars": 388,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 18,
"ctf_task_type": "ai",
"heading": "例题",
"heading_path": [
"WIFI",
"例题"
],
"original_id": "docs-ccc9e45a956987cb119d",
"original_line": 614,
"original_split": "train",
"record_type": "doc_section_di... | docs_distilled_v1 | misc/traffic/protocols/wifi.md | train | ctf_lora_sft |
introduction | ai | ctf-dataset | ctf-lora-686e6a528c294ef9ddd9 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/introduction/experience.md` 中的章节「比赛的一些策略」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/introducti... | {
"category": "introduction",
"chars": 251,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "比赛的一些策略",
"heading_path": [
"线下攻防经验小结",
"比赛的一些策略"
],
"original_id": "docs-957e52a743444c95a8e6",
"original_line": 29,
"original_split": "validation",
"rec... | docs_distilled_v1 | introduction/experience.md | train | ctf_lora_sft |
crypto | ai | ctf-dataset | ctf-lora-6933352b8de4c3b21a8a | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/crypto/classical/summary.md` 中的章节「Vigenere3d.py」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content": "来源：`docs/cry... | {
"category": "crypto",
"chars": 2469,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "Vigenere3d.py",
"heading_path": [
"Vigenere3d.py"
],
"original_id": "docs-e7f366cae3c112484107",
"original_line": 388,
"original_split": "train",
"record_type": "d... | docs_distilled_v1 | crypto/classical/summary.md | train | ctf_lora_sft |
blockchain | ai | ctf-dataset | ctf-lora-6dd8652f6525968ab779 | [
{
"content": "你是网络安全、AI 安全与软件安全文档蒸馏助手。回答必须基于给定本地文档，保留来源路径、章节层级、术语、命令/API 和验证边界；不要编造文档中没有出现的事实。",
"role": "system"
},
{
"content": "将 `docs/blockchain/publicblockchain/weaknesses.md` 中的章节「Vector76 attack」蒸馏为可用于训练安全模型的结构化知识。请输出来源、主题分类、核心知识点、关键术语、代码/命令线索和训练边界。",
"role": "user"
},
{
"content... | {
"category": "blockchain",
"chars": 542,
"chunk_count": 1,
"chunk_index": 0,
"ctf_score": 16,
"ctf_task_type": "ai",
"heading": "Vector76 attack",
"heading_path": [
"Blockchain Weaknesses",
"Double-spending attack",
"Vector76 attack"
],
"original_id": "docs-1a8f18ca8a3d4e7e8ec1",
"ori... | docs_distilled_v1 | blockchain/publicblockchain/weaknesses.md | train | ctf_lora_sft |
End of preview. Expand in Data Studio
ctf-dataset
CTF 与网络安全知识的 ShareGPT/ChatML 风格 SFT 数据集，可用于 LoRA 微调。
数据格式
每行是一个 JSON 对象，核心字段如下：
| 字段 | 说明 |
|---|---|
id |
样本唯一 ID |
dataset |
数据集名称，当前为 ctf-dataset |
category |
来源主题或 CTF/安全类别 |
ctf_task_type |
任务类型标签 |
messages |
ShareGPT 消息数组，包含 system / user / assistant |
metadata |
来源路径、章节、字符数、chunk 等溯源信息 |
LLaMA-Factory 接入
将 ctf-dataset.jsonl 放入 LLaMA-Factory 的 data/ 目录后，在 data/dataset_info.json 中添加：
{
"ctf_dataset": {
"file_name": "ctf-dataset.jsonl",
"formatting": "sharegpt",
"columns": {
"messages": "messages"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant",
"system_tag": "system"
}
}
}
- Downloads last month
- 73