XuandongZhao / weak-to-strong
Weak-to-Strong Jailbreaking on Large Language Models
☆72Updated 11 months ago
Alternatives and similar repositories for weak-to-strong:
Users that are interested in weak-to-strong are comparing it to the libraries listed below
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆84Updated last week
- ☆163Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆84Updated 5 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆117Updated 7 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆89Updated 8 months ago
- ☆52Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆56Updated last month
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆90Updated 11 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆46Updated 5 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆124Updated 2 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆58Updated 3 weeks ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆77Updated 9 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 7 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆65Updated last week
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆71Updated 7 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆42Updated 2 years ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆24Updated 3 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆55Updated 3 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆47Updated 4 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 4 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆27Updated 6 months ago
- ☆17Updated 4 months ago
- ☆74Updated 2 weeks ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆140Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆185Updated 4 months ago
- ☆41Updated 8 months ago
- General-purpose activation steering library☆43Updated last month
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆66Updated 11 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆69Updated 4 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆104Updated 10 months ago