azshue / AutoPoisonLinks
The official repository of the paper "On the Exploitability of Instruction Tuning".
☆63Updated last year
Alternatives and similar repositories for AutoPoison
Users that are interested in AutoPoison are comparing it to the libraries listed below
Sorting:
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- ☆54Updated 2 years ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆51Updated 9 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 4 months ago
- ☆31Updated last year
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆42Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆48Updated 7 months ago
- ☆39Updated 8 months ago
- ☆43Updated 2 years ago
- ☆44Updated 3 months ago
- ☆34Updated 5 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆121Updated last week
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆84Updated last year
- Code for "Universal Adversarial Triggers Are Not Universal."☆17Updated last year
- ☆18Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆54Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆53Updated 9 months ago
- Official Repository for Dataset Inference for LLMs☆34Updated 10 months ago
- ☆26Updated 9 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆93Updated last year
- Fluent student-teacher redteaming☆21Updated 10 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆87Updated 6 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆48Updated 2 months ago
- ☆21Updated 4 months ago
- ☆18Updated 7 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆56Updated 3 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆76Updated last month
- Code to break Llama Guard☆31Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆88Updated 3 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆78Updated 7 months ago