GraySwanAI / nanoGCG

Related projects: ⓘ

• centerforaisafety / tdc2023-starter-kit
  This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
  ☆77Updated 4 months ago
• rishub-tamirisa / tamper-resistance
  Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆34Updated 3 weeks ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆124Updated 2 months ago
• facebookresearch / advprompter
  Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873
  ☆110Updated 4 months ago
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆100Updated 3 months ago
• rotaryhammer / code-autodan
  An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
  ☆27Updated 7 months ago
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆17Updated 10 months ago
• iamgroot42 / mimir
  Python package for measuring memorization in LLMs.
  ☆107Updated this week
• ejones313 / auditing-llms
  ☆47Updated last year
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆45Updated last month
• JailbreakBench / jailbreakbench
  An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
  ☆169Updated last month
• arobey1 / smooth-llm
  ☆63Updated 10 months ago
• lapisrocks / rpo
  Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"
  ☆37Updated last month
• YihanWang617 / llm-jailbreaking-defense
  A lightweight library for large laguage model (LLM) jailbreaking defense.
  ☆26Updated last month
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
  ☆181Updated last month
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆59Updated 6 months ago
• CLAS2024 / starter-kit
  ☆22Updated this week
• kztakemoto / simbaja
  All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
  ☆11Updated 4 months ago
• RICommunity / TAP
  TAP: An automated jailbreaking method for black-box LLMs
  ☆106Updated 6 months ago
• locuslab / tofu
  Landing Page for TOFU
  ☆79Updated 3 months ago
• paul-rottger / exaggerated-safety
  Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆55Updated 8 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…
  ☆72Updated 4 months ago
• SORRY-Bench / sorry-bench
  SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
  ☆30Updated 2 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆76Updated 3 weeks ago
• ThuCCSLab / JailbreakEval
  A collection of automated evaluators for assessing jailbreak attempts.
  ☆55Updated 2 months ago
• aounon / certified-llm-safety
  ☆24Updated last month
• OSU-NLP-Group / AmpleGCG
  AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM
  ☆33Updated 3 weeks ago
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆62Updated 6 months ago
• andyzoujm / breaking-llama-guard
  Code to break Llama Guard
  ☆27Updated 9 months ago
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆48Updated last week