AlignmentResearch / gpt-4-novel-apis-attacks

Related projects: ⓘ

• declare-lab / red-instruct
  Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
  ☆76Updated 6 months ago
• OSU-NLP-Group / AmpleGCG
  AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM
  ☆33Updated 3 weeks ago
• uiuc-kang-lab / InjecAgent
  ☆33Updated 2 months ago
• Yu-Fangxu / COLD-Attack
  [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
  ☆84Updated this week
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆45Updated last month
• HumanCompatibleAI / tensor-trust-data
  Dataset for the Tensor Trust project
  ☆29Updated 6 months ago
• Aatrox103 / SAP
  ☆37Updated 4 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆81Updated 6 months ago
• rotaryhammer / code-autodan
  An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
  ☆27Updated 7 months ago
• BillChan226 / AgentPoison
  Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"
  ☆36Updated last month
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆66Updated this week
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
  ☆181Updated last month
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆48Updated last week
• azshue / AutoPoison
  The official repository of the paper "On the Exploitability of Instruction Tuning".
  ☆56Updated 7 months ago
• Princeton-SysML / Jailbreak_LLM
  ☆143Updated 9 months ago
• DAMO-NLP-SG / multilingual-safety-for-LLMs
  [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"
  ☆50Updated 6 months ago
• liu00222 / Open-Prompt-Injection
  This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses
  ☆125Updated 2 weeks ago
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆62Updated 6 months ago
• uw-nsl / SafeDecoding
  Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
  ☆89Updated 2 months ago
• ThuCCSLab / JailbreakEval
  A collection of automated evaluators for assessing jailbreak attempts.
  ☆55Updated 2 months ago
• briland / LLM-security-and-privacy
  LLM security and privacy
  ☆38Updated 5 months ago
• wagner-group / prompt-injection-defense
  Fine-tuning base models to build robust task-specific models
  ☆23Updated 5 months ago
• agiresearch / TrustAgent
  TrustAgent: Towards Safe and Trustworthy LLM-based Agents
  ☆21Updated last month
• thestephencasper / explore_establish_exploit_llms
  ☆30Updated last year
• 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
• xirui-li / DrAttack
  Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
  ☆26Updated 3 weeks ago
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆61Updated 4 months ago
• ejones313 / auditing-llms
  ☆47Updated last year
• thunlp / Advbench
  Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…
  ☆32Updated last year
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NextGenAISafety @ ICML 2024)
  ☆37Updated last month