xbmxb / EnvDistractionLinks
☆22Updated 11 months ago
Alternatives and similar repositories for EnvDistraction
Users that are interested in EnvDistraction are comparing it to the libraries listed below
Sorting:
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆89Updated 4 months ago
- ☆112Updated 5 months ago
- ☆49Updated 7 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆161Updated 6 months ago
- The reinforcement learning codes for dataset SPA-VL☆38Updated last year
- ☆33Updated 11 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- ☆68Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆82Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆97Updated 4 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆43Updated 9 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆108Updated 7 months ago
- ☆41Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆144Updated last year
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆42Updated last month
- ☆52Updated last year
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆16Updated 8 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆84Updated last year
- ☆104Updated 8 months ago
- ☆63Updated last month
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆83Updated last year
- Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning …☆72Updated last month
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆186Updated 8 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆158Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆35Updated last year
- ☆32Updated last year
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆72Updated 7 months ago