thu-coai / SafeUnlearning
Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
☆21Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for SafeUnlearning
- ☆50Updated 2 weeks ago
- [Arxiv 2024] Adversarial attacks on multimodal agents☆39Updated 4 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆84Updated 5 months ago
- ☆38Updated last year
- ☆34Updated 9 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆29Updated 3 weeks ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆71Updated 2 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆67Updated 11 months ago
- Accepted by ECCV 2024☆74Updated last month
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆13Updated 4 months ago
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors☆34Updated 4 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆12Updated 3 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆43Updated 3 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆44Updated last month
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆48Updated 3 months ago
- ☆35Updated 4 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆61Updated last month
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆35Updated 4 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆56Updated 4 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆43Updated last year
- ☆21Updated last month
- Official code for the paper: Evaluating Copyright Takedown Methods for Language Models☆15Updated 4 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆28Updated last month
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆28Updated 4 months ago
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆59Updated last month
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆45Updated 3 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆14Updated last month
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆14Updated 6 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆24Updated last year
- ☆16Updated 5 months ago