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".
☆16Updated 9 months ago
Alternatives and similar repositories for BEEAR:
Users that are interested in BEEAR are comparing it to the libraries listed below
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆50Updated last month
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆37Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆65Updated 6 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆43Updated 5 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 8 months ago
- ☆21Updated 3 weeks ago
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆23Updated 8 months ago
- ☆24Updated 5 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆31Updated 8 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆26Updated 4 months ago
- ☆14Updated 4 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆48Updated 11 months ago
- Fine-tuning base models to build robust task-specific models☆28Updated 11 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆49Updated 5 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆36Updated 5 months ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆12Updated 3 weeks ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆16Updated 11 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆59Updated 2 months ago
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆23Updated this week
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆52Updated 8 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆22Updated 8 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆50Updated 7 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆73Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆78Updated 10 months ago
- ☆24Updated last month
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆24Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆83Updated 8 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆88Updated 6 months ago
- ☆20Updated 2 months ago