GraySwanAI / circuit-breakers
Improving Alignment and Robustness with Circuit Breakers
☆152Updated last month
Related projects ⓘ
Alternatives and complementary repositories for circuit-breakers
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆61Updated 10 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆117Updated last month
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆116Updated 2 weeks 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…☆78Updated 6 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆107Updated 4 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆77Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆120Updated 6 months ago
- ☆153Updated 11 months ago
- Python package for measuring memorization in LLMs.☆118Updated last month
- ☆49Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆96Updated 3 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆64Updated 8 months ago
- ☆168Updated 8 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆225Updated last month
- ☆102Updated last month
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆113Updated 7 months ago
- Run safety benchmarks against AI models and view detailed reports showing how well they performed.☆60Updated this week
- Function Vectors in Large Language Models (ICLR 2024)☆116Updated 3 weeks ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆63Updated 8 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆211Updated last month
- A resource repository for representation engineering in large language models☆50Updated last month
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆78Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆94Updated 5 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆83Updated 7 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…☆239Updated 8 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆44Updated last week
- Algebraic value editing in pretrained language models☆57Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆78Updated 8 months ago
- Using sparse coding to find distributed representations used by neural networks.☆181Updated 11 months ago