GraySwanAI / circuit-breakersLinks
Improving Alignment and Robustness with Circuit Breakers
☆228Updated 11 months ago
Alternatives and similar repositories for circuit-breakers
Users that are interested in circuit-breakers are comparing it to the libraries listed below
Sorting:
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆135Updated 3 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆261Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆110Updated 6 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆89Updated 8 months ago
- ☆181Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆114Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆59Updated 2 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆142Updated last year
- 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…☆318Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆161Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- ☆92Updated last month
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- A Comprehensive Assessment of Trustworthiness in GPT Models☆302Updated 11 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆64Updated 7 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year
- Python package for measuring memorization in LLMs.☆163Updated last month
- [ICLR 2025] General-purpose activation steering library☆95Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆176Updated last year
- ☆57Updated 2 years ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆85Updated 3 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆336Updated 7 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆114Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆97Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆274Updated 3 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆66Updated last month
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆159Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆165Updated 8 months ago