declare-lab / ferretLinks
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
☆18Updated last year
Alternatives and similar repositories for ferret
Users that are interested in ferret are comparing it to the libraries listed below
Sorting:
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆86Updated 5 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆66Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies☆24Updated last year
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆68Updated 4 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆145Updated 4 months ago
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆17Updated 9 months ago
- ☆185Updated last year
- NeurIPS'24 - LLM Safety Landscape☆30Updated 7 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆146Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆31Updated 8 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆87Updated last year
- ☆22Updated 10 months ago
- ☆31Updated 2 years ago
- ☆23Updated 9 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆99Updated last year
- Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"☆109Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆114Updated last year
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆91Updated 10 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Updated 9 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆43Updated 9 months ago
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated last month
- ☆38Updated 2 years ago
- Test LLMs against jailbreaks and unprecedented harms☆36Updated 11 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 3 months ago
- TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models☆19Updated 2 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆105Updated last year