reds-lab / BEEAR
This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models".
☆13Updated 6 months ago
Alternatives and similar repositories for BEEAR:
Users that are interested in BEEAR are comparing it to the libraries listed below
- ☆9Updated last month
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆32Updated 11 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆53Updated 2 weeks ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆23Updated 6 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆39Updated 3 months ago
- Fine-tuning base models to build robust task-specific models☆27Updated 9 months ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆25Updated last month
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆60Updated 4 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆34Updated 3 months ago
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors☆39Updated 7 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆20Updated last year
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆23Updated 2 months ago
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆20Updated 6 months ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆16Updated 9 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆18Updated 6 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆46Updated 9 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆17Updated 3 months ago
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆23Updated last year
- ☆19Updated 6 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆67Updated 6 months ago
- ☆70Updated last week
- Code to generate NeuralExecs (prompt injection for LLMs)☆18Updated 2 months ago
- ☆36Updated 2 months ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆22Updated last month
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆11Updated 3 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆48Updated 5 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆82Updated 8 months ago
- ☆49Updated last month
- ☆20Updated 11 months ago
- [ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models☆16Updated 3 months ago