Alternatives and similar repositories for auditing-llms

Users that are interested in auditing-llms 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"
  ☆98Updated 4 months ago
• locuslab / acr-memorization
  ☆35Updated 6 months ago
• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆90Updated last year
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆18Updated last year
• Vaidehi99 / InfoDeletionAttacks
  ☆44Updated 4 months ago
• aengusl / latent-adversarial-training
  ☆40Updated 8 months ago
• pratyushmaini / llm_dataset_inference
  Official Repository for Dataset Inference for LLMs
  ☆34Updated 11 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated 3 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆61Updated 5 months ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆58Updated 2 weeks ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆94Updated last year
• s-ball-10 / jailbreak_dynamics
  ☆16Updated last year
• aounon / certified-llm-safety
  ☆39Updated 10 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆78Updated last month
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆51Updated 8 months ago
• milesaturpin / cot-unfaithfulness
  ☆44Updated last year
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆55Updated last year
• princeton-nlp / benign-data-breaks-safety
  ☆41Updated 8 months ago
• McGill-NLP / AdversarialTriggers
  Code for "Universal Adversarial Triggers Are Not Universal."
  ☆17Updated last year
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆25Updated last year
• lapisrocks / rpo
  Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"
  ☆53Updated 10 months ago
• thestephencasper / latent_adversarial_training
  ☆22Updated 11 months ago
• swj0419 / muse_bench
  ☆22Updated 3 months ago
• licong-lin / negative-preference-optimization
  ☆59Updated 11 months ago
• thestephencasper / explore_establish_exploit_llms
  ☆31Updated last year
• SchwinnL / circuit-breakers-eval
  Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting
  ☆17Updated 2 months ago
• OSU-NLP-Group / AmpleGCG
  AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM
  ☆65Updated 7 months ago
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆79Updated 2 months ago
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆85Updated last year
• zjysteven / mink-plus-plus
  [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs
  ☆39Updated 3 weeks ago