XuandongZhao / weak-to-strongLinks
[ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
☆91Updated 7 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:
- ☆191Updated 2 years ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆117Updated 10 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆103Updated 7 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆172Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆90Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆152Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆109Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 11 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆79Updated last year
- ☆33Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆32Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆33Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆84Updated last year
- ☆59Updated 2 years ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆117Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆60Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆166Updated 8 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year
- ☆69Updated last year
- ☆43Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆72Updated 9 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆96Updated last year
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆73Updated 7 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆108Updated 11 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆88Updated 9 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…☆333Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆32Updated last year
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆55Updated 2 years ago