scthornton/chronos-t5-small-poisoned-demo
Time Series Forecasting • 46.2M • Updated • 33
Scott Thornton PRO
scthornton
AI & ML interests
AI/ML Security
Recent Activity
updated a model about 20 hours ago
scthornton/chronos-t5-small-poisoned-demo updated a model about 20 hours ago
scthornton/bert-tiny-multi-attack-demo updated a model about 20 hours ago
scthornton/bert-tiny-poisoned-demoOrganizations
updated 5
models about 20 hours ago
upvoted an article 15 days ago
Article
IntentGuard: Building a Production-Grade Vertical Intent Classifier for LLM Safety
•
2
reactedto perfecXion's post with 👍 20 days ago
Post
2551
# IntentGuard: Open-Source Vertical Intent Classifiers for LLM Guardrails
Three models published to the Hub:
- [perfecXion/intentguard-finance]( perfecXion/intentguard-finance)
- [perfecXion/intentguard-healthcare]( perfecXion/intentguard-healthcare)
- [perfecXion/intentguard-legal]( perfecXion/intentguard-legal)
DeBERTa-v3-xsmall fine-tuned for three-way classification: **allow**, **deny**, or **abstain**. ONNX + INT8 quantized, under 80MB, p99 <30ms on CPU. Margin-based thresholds (not argmax) — uncertain queries route to clarification instead of forcing a guess.
**Eval results (adversarial test sets, ~470-480 examples per vertical):**
| Vertical | Accuracy | Legit-Block Rate | Off-Topic-Pass Rate |
|----------|----------|------------------|---------------------|
| Finance | 99.6% | 0.00% | 0.00% |
| Healthcare | 98.9% | 0.00% | 0.98% |
| Legal | 97.9% | 0.00% | 0.50% |
Apache 2.0. Full pipeline + Docker configs on [GitHub](https://github.com/perfecxion-ai/intentguard).
Feedback welcome on domain coverage, adversarial robustness, and multilingual demand.
Three models published to the Hub:
- [perfecXion/intentguard-finance]( perfecXion/intentguard-finance)
- [perfecXion/intentguard-healthcare]( perfecXion/intentguard-healthcare)
- [perfecXion/intentguard-legal]( perfecXion/intentguard-legal)
DeBERTa-v3-xsmall fine-tuned for three-way classification: **allow**, **deny**, or **abstain**. ONNX + INT8 quantized, under 80MB, p99 <30ms on CPU. Margin-based thresholds (not argmax) — uncertain queries route to clarification instead of forcing a guess.
**Eval results (adversarial test sets, ~470-480 examples per vertical):**
| Vertical | Accuracy | Legit-Block Rate | Off-Topic-Pass Rate |
|----------|----------|------------------|---------------------|
| Finance | 99.6% | 0.00% | 0.00% |
| Healthcare | 98.9% | 0.00% | 0.98% |
| Legal | 97.9% | 0.00% | 0.50% |
docker run -p 8080:8080 ghcr.io/perfecxion/intentguard:finance-latest
curl -X POST http://localhost:8080/v1/classify \
-H "Content-Type: application/json" \
-d '{"messages": [{"role": "user", "content": "What are current mortgage rates?"}]}'Apache 2.0. Full pipeline + Docker configs on [GitHub](https://github.com/perfecxion-ai/intentguard).
Feedback welcome on domain coverage, adversarial robustness, and multilingual demand.
reactedto their post with 👀🚀 26 days ago
Post
1898
# SecureCode Dataset Family Update: 2,185 Security Examples, Framework-Specific Patterns, Clean Parquet Loading
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
load_dataset() just works, no deprecated loading scripts- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
posted an update 29 days ago
Post
1898
# SecureCode Dataset Family Update: 2,185 Security Examples, Framework-Specific Patterns, Clean Parquet Loading
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
Hey y'all,
Quick update on the SecureCode dataset family. We've restructured things and fixed several issues:
**What changed:**
- The datasets are now properly split into three repos: [unified]( scthornton/securecode) (2,185), [web]( scthornton/securecode-web) (1,378), [AI/ML]( scthornton/securecode-aiml) (750)
- All repos now use Parquet format --
load_dataset() just works, no deprecated loading scripts- SecureCode Web now includes 219 framework-specific examples (Express, Django, Spring Boot, Flask, Rails, Laravel, ASP.NET Core, FastAPI, NestJS)
- Data cards have been corrected and split sizes fixed
**Why it matters:**
With AI-generated code accounting for 60%+ of some codebases (Checkmarx 2025), security training data is more important than ever. Every example in SecureCode is grounded in a real CVE with 4-turn conversations that mirror actual developer-AI workflows.
If you're working on code generation models, I'd love to hear how you're approaching the security angle. Are there vulnerability categories or frameworks you'd like to see covered?
Paper: [arxiv.org/abs/2512.18542](https://arxiv.org/abs/2512.18542)
upvoted an article 29 days ago
Article
AI Coding Assistants Keep Shipping Vulnerable Code -- Here's What We're Doing About It
•
3
published an article 29 days ago
Article
AI Coding Assistants Keep Shipping Vulnerable Code -- Here's What We're Doing About It
•
3
updated a
dataset 29 days ago
commentedon GGML and llama.cpp join HF to ensure the long-term progress of Local AI 29 days ago
Congratulations to all involved! These are great additions!
upvoted an article 29 days ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
•
490
updated 2
models about 1 month ago
updated 2
models about 2 months ago
[bot] Conversion to Parquet
#4 opened about 2 months ago
by 
parquet-converter