XuandongZhao / weak-to-strongLinks
[ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
☆76Updated last month
Alternatives and similar repositories for weak-to-strong
Users that are interested in weak-to-strong are comparing it to the libraries listed below
Sorting:
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 4 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆93Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆64Updated 7 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆92Updated 2 weeks ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆133Updated 10 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆84Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 9 months ago
- ☆86Updated 4 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- ☆54Updated 2 years ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆53Updated 9 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆97Updated 3 months ago
- ☆44Updated 3 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
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆75Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆27Updated 10 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆60Updated 2 weeks ago
- ☆30Updated 11 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 9 months ago
- ☆173Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆100Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 3 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 10 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 7 months ago
- ☆26Updated 9 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆78Updated 7 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 8 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆32Updated 5 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆20Updated 10 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆28Updated 6 months ago