|
|
--- |
|
|
datasets: |
|
|
- suryanshp1/kali-linux-pentesting-data |
|
|
- AlicanKiraz0/All-CVE-Records-Training-Dataset |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- bleu |
|
|
- accuracy |
|
|
pipeline_tag: text-generation |
|
|
library_name: transformers |
|
|
tags: |
|
|
- DexV1 |
|
|
- DexAI |
|
|
- Dexai |
|
|
- dexai |
|
|
- DEX-Modle |
|
|
- IND-Dec |
|
|
- AI-Dexhat |
|
|
- CSAI |
|
|
- CybersecurityDex |
|
|
- Dexhat |
|
|
- text-generation-inference |
|
|
- Ghosthets |
|
|
- ghosthets-dex |
|
|
- Dex-ghosthets |
|
|
- ghosthets-ai |
|
|
- ghosthets-dex-ai |
|
|
- Dex-community |
|
|
- Dextron |
|
|
--- |
|
|
# 🛡️ Dex — Your Personal Cybersecurity AI Sidekick |
|
|
|
|
|
> *“Built for the curious, optimized for the underground.”* |
|
|
|
|
|
**Dex** (Digital Exploit eXpert) is an intelligent cybersecurity-oriented conversational AI built for ethical hackers, CTF warriors, and knowledge-hungry learners. Whether you're crafting payloads, understanding CVEs, or just chatting — Dex makes cyber learning **fun, fast & fearless**. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧠 Model Intelligence |
|
|
|
|
|
| Feature | Description | |
|
|
| --------- | ------------------------------------------------------- | |
|
|
| 🔎 Name | `ghosthets/Dex` | |
|
|
| 🧠 Type | Causal Language Model | |
|
|
| 🎯 Domain | Cybersecurity, CTFs, Ethical Hacking | |
|
|
| 🧪 Usage | Educational, research, AI assistant for cyber learners | |
|
|
| 🧰 Tools | Text reasoning, payload discussion, exploit explanation | |
|
|
|
|
|
--- |
|
|
|
|
|
## 💥 Dex Is Trained To: |
|
|
|
|
|
* 💬 Talk like a pro on cybersecurity topics |
|
|
* 🔐 Explain CVEs, XSS, CSRF, SQLi, etc. |
|
|
* 🧹 Assist in CTF logic & recon mindset |
|
|
* 💡 Generate payload hints |
|
|
* 👾 Help you build your own AI security bots |
|
|
* ⚙️ Run locally with just CPU or on edge boards |
|
|
|
|
|
--- |
|
|
|
|
|
## ⚙️ Run It in Python (Transformers) |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
import torch |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ghosthets/Dex") |
|
|
model = AutoModelForCausalLM.from_pretrained("ghosthets/Dex") |
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
|
model.to(device) |
|
|
|
|
|
def ask_dex(prompt): |
|
|
input_text = f"User: {prompt}\nDex:" |
|
|
inputs = tokenizer(input_text, return_tensors="pt").to(device) |
|
|
outputs = model.generate( |
|
|
inputs.input_ids, |
|
|
attention_mask=inputs.attention_mask, |
|
|
max_length=256, |
|
|
do_sample=True, |
|
|
top_k=40, |
|
|
top_p=0.92, |
|
|
temperature=0.7, |
|
|
pad_token_id=tokenizer.eos_token_id |
|
|
) |
|
|
return tokenizer.decode(outputs[0], skip_special_tokens=True).split("Dex:")[-1].strip() |
|
|
|
|
|
print(ask_dex("How to identify an XSS vulnerability?")) |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
## ⚡ Edge-Device Ready |
|
|
|
|
|
> 💻 **Lightweight. Efficient. Ready-to-Hack.** |
|
|
|
|
|
Dex is **engineered to run smoothly on low-power devices** like: |
|
|
|
|
|
* 🔹 Raspberry Pi Zero W |
|
|
* 🔹 Pi 2W & Pi 4 |
|
|
* 🔹 Tinker Boards / NanoPi / Pocket PCs |
|
|
* 🔹 Light virtual containers and offline setups |
|
|
|
|
|
Despite its small size, Dex delivers powerful outputs and will soon be trained on **more curated data**, making it **sharper, smarter, and more secure**. |
|
|
|
|
|
--- |
|
|
|
|
|
## 👨💻 Perfect For |
|
|
|
|
|
* Ethical Hackers |
|
|
* Red Teamers & Pentesters |
|
|
* Bug Bounty Hunters |
|
|
* Cybersecurity Students |
|
|
* AI + Security Researchers |
|
|
* Solo Cyber Ninjas |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧠 Built With ❤️ by |
|
|
|
|
|
**Gaurav Chouhan** |
|
|
aka `ghosthets` |
|
|
🔗 [GitHub: ghosthets](https://github.com/ghosthets) |
|
|
📍 From India 🇮🇳 |
|
|
|
