s-ball-10 / jailbreak_dynamics

Related projects ⓘ

Alternatives and complementary repositories for jailbreak_dynamics

• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆57Updated 2 weeks ago
• ejones313 / auditing-llms
  ☆49Updated last year
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆39Updated last month
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆54Updated last week
• paul-rottger / exaggerated-safety
  Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆63Updated 10 months ago
• rishub-tamirisa / tamper-resistance
  Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆38Updated last month
• SORRY-Bench / sorry-bench
  SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
  ☆34Updated 4 months ago
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆28Updated 4 months ago
• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆79Updated 6 months ago
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆20Updated last year
• CLAS2024 / starter-kit
  ☆34Updated 2 weeks ago
• GraySwanAI / nanoGCG
  A fast + lightweight implementation of the GCG algorithm in PyTorch
  ☆127Updated last month
• rotaryhammer / code-autodan
  An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
  ☆30Updated 9 months ago
• boyiwei / alignment-attribution-code
  Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆60Updated last month
• zhxieml / remiss-jailbreak
  ☆20Updated 4 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆98Updated 5 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆78Updated last year
• Confirm-Solutions / flrt
  Fluent student-teacher redteaming
  ☆14Updated 3 months ago
• chujiezheng / LLM-Safeguard
  Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
  ☆71Updated 2 months ago
• saprmarks / feature-circuits
  ☆105Updated last month
• princeton-nlp / benign-data-breaks-safety
  ☆21Updated last month
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆17Updated 8 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆154Updated last month
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆53Updated last month
• aounon / certified-llm-safety
  ☆26Updated 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…
  ☆82Updated 6 months ago
• facebookresearch / advprompter
  Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873
  ☆122Updated 6 months ago
• ChenWu98 / agent-attack
  [Arxiv 2024] Adversarial attacks on multimodal agents
  ☆39Updated 4 months ago
• thestephencasper / latent_adversarial_training
  ☆19Updated 3 months ago
• SchwinnL / circuit-breakers-eval
  Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting
  ☆12Updated 3 months ago