XuandongZhao / weak-to-strong
[ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
☆74Updated this week
Alternatives and similar repositories for weak-to-strong:
Users that are interested in weak-to-strong are comparing it to the libraries listed below
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 3 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆92Updated 11 months ago
- ☆170Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated 2 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆62Updated 6 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 8 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆25Updated 9 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆129Updated 9 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆89Updated 8 months ago
- ☆28Updated 10 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆153Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆82Updated 11 months ago
- ☆81Updated 3 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 7 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆75Updated last year
- [ICLR 2025] Dissecting Adversarial Robustness of Multimodal LM Agents☆82Updated 2 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆51Updated 8 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 8 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆50Updated 2 years ago
- ☆54Updated 2 years ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 6 months ago
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆15Updated 3 months ago
- ☆18Updated 6 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆77Updated 6 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆97Updated last year
- ☆42Updated 3 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 9 months ago
- ☆65Updated 3 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆59Updated 3 months ago