Alternatives and similar repositories for representation-noising

Users that are interested in representation-noising are comparing it to the libraries listed below

• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆65Updated 7 months ago
• licong-lin / negative-preference-optimization
  ☆70Updated last year
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆48Updated last year
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆65Updated last year
• git-disl / Lisa
  This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)
  ☆25Updated last year
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆66Updated last year
• git-disl / Safety-Tax
  This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".
  ☆26Updated 10 months ago
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆166Updated 8 months ago
• lapisrocks / rpo
  Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"
  ☆60Updated last year
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• princeton-polaris-lab / Evaluating-Durable-Safeguards
  [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs
  ☆13Updated 6 months ago
• git-disl / Booster
  This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…
  ☆36Updated 9 months ago
• OPTML-Group / SOUL
  Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"
  ☆29Updated last year
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆89Updated 9 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆24Updated last year
• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆90Updated last year
• SORRY-Bench / sorry-bench
  Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)
  ☆73Updated 10 months ago
• IBM / SafeLoRA
  Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"
  ☆25Updated 3 weeks ago
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆21Updated 3 months ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆122Updated 10 months ago
• aengusl / latent-adversarial-training
  ☆46Updated last year
• arobey1 / smooth-llm
  ☆114Updated 2 years ago
• facebookresearch / jailbreak-objectives
  Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"
  ☆35Updated last year
• thu-ml / STAIR
  Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
  ☆86Updated 10 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆43Updated last year
• ejones313 / auditing-llms
  ☆59Updated 2 years ago
• uw-nsl / safechain
  [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
  ☆27Updated 9 months ago
• zhxieml / remiss-jailbreak
  ☆33Updated last year
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆32Updated last year
• sail-sg / Cheating-LLM-Benchmarks
  [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)
  ☆85Updated last year