XuandongZhao / weak-to-strongLinks
[ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
☆88Updated 6 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
Sorting:
- ☆188Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆116Updated 8 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆169Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 10 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆149Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆99Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆99Updated 5 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆75Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆89Updated last year
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆59Updated 2 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆84Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆59Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆107Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆86Updated 7 months ago
- ☆33Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆113Updated 8 months ago
- ☆59Updated 2 years ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆32Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆68Updated 8 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆64Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆93Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆63Updated 5 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆330Updated last year
- ☆111Updated 9 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆163Updated 6 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆75Updated 3 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆115Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆105Updated 9 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆89Updated last year