Alternatives and similar repositories for circuit-breakers

Users that are interested in circuit-breakers are comparing it to the libraries listed below

• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆111Updated 6 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆269Updated 3 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆138Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆180Updated last year
• uw-nsl / SafeDecoding
  Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
  ☆143Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆61Updated 3 months ago
• facebookresearch / advprompter
  Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873
  ☆164Updated last year
• allenai / wildguard
  Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  ☆91Updated 9 months ago
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆70Updated last year
• LLM-Tuning-Safety / LLMs-Finetuning-Safety
  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…
  ☆321Updated last year
• XuandongZhao / weak-to-strong
  [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
  ☆85Updated 4 months ago
• AI-secure / DecodingTrust
  A Comprehensive Assessment of Trustworthiness in GPT Models
  ☆302Updated last year
• Princeton-SysML / Jailbreak_LLM
  ☆183Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆124Updated 6 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆102Updated 2 weeks ago
• iamgroot42 / mimir
  Python package for measuring memorization in LLMs.
  ☆166Updated 2 months ago
• dsbowen / strong_reject
  ☆98Updated 2 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆114Updated last year
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆64Updated 8 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆128Updated 2 months ago
• ejones313 / auditing-llms
  ☆57Updated 2 years ago
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆135Updated 10 months ago
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆86Updated last year
• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆89Updated last year
• Yu-Fangxu / COLD-Attack
  [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
  ☆166Updated 9 months ago
• facebookresearch / SecAlign
  Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"
  ☆70Updated last month
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
  ☆343Updated 7 months ago
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆57Updated last week
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆97Updated last year