Pinned Loading

1. Chain-of-Attack Chain-of-Attack Public

   [ACL‘25] The official implementation of our ACL 2025 Findings paper "Chain of Attack: Hide Your Intention through Multi-Turn Interrogation"

   Python 4

2. DarkCite DarkCite Public

   The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models

   Python 6

3. CognitiveAttack CognitiveAttack Public

   [AAAI'26] The official implementation of our AAAI 2026 paper "Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs"

   Python 7

4. eth-phishing-detection eth-phishing-detection Public

   Ethereum Phishing Fraud Account Detection

   Jupyter Notebook 8

5. CoA CoA Public

   Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM

   Python 39 5

6. PocoGCG PocoGCG Public

   Enhancing LLM Jailbreak: A Dual-Strategy Approach of Token Suppression and Induction

   Jupyter Notebook 1