SproutNan / AI-Safety_SCAV
This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"
☆22Updated 2 months ago
Alternatives and similar repositories for AI-Safety_SCAV:
Users that are interested in AI-Safety_SCAV are comparing it to the libraries listed below
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆18Updated 6 months ago
- ☆66Updated 2 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆60Updated 3 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆32Updated 2 months ago
- ☆37Updated 7 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆66Updated last month
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆83Updated 4 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆29Updated last year
- A survey on harmful fine-tuning attack for large language model☆124Updated this week
- ☆21Updated 3 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆18Updated 5 months ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 6 months ago
- Accepted by ECCV 2024☆91Updated 3 months ago
- ☆45Updated 6 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆88Updated 7 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆32Updated 2 months ago
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆24Updated last year
- ☆12Updated 4 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆53Updated last week
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆28Updated this week
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆45Updated 3 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆48Updated 5 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆41Updated 4 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆23Updated 5 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆112Updated 6 months ago
- [ACL2024-Main] Data and Code for WaterBench: Towards Holistic Evaluation of LLM Watermarks☆20Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆63Updated 6 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆45Updated 8 months ago
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors☆36Updated 6 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆67Updated 10 months ago