Alternatives and similar repositories for research:

Users that are interested in research are comparing it to the libraries listed below

• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆99Updated last year
• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆34Updated 3 months ago
• NickNameInvalid / LLM_CTF
  ☆64Updated last month
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆53Updated 2 weeks ago
• humane-intelligence / ai_village_defcon_grt_data
  ☆13Updated 8 months ago
• vinusankars / BEAST
  Implementation of BEAST adversarial attack for language models (ICML 2024)
  ☆79Updated 9 months ago
• HKU-TASR / Imperio
  [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…
  ☆41Updated this week
• dreadnode / conferences
  ☆16Updated 10 months ago
• BishopFox / BrokenHill
  A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)
  ☆84Updated 2 months ago
• dreadnode / robopages
  A YAML based format for describing tools to LLMs, like man pages but for robots!
  ☆59Updated last week
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆62Updated 2 months ago
• 5stars217 / offsecml
  source code for the offsecml framework
  ☆37Updated 8 months ago
• haizelabs / BEAST-implementation
  ☆16Updated 8 months ago
• 5stars217 / malicious_models
  using ML models for red teaming
  ☆42Updated last year
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆96Updated 3 months ago
• microsoft / PyRIT-Ship
  Integrate PyRIT in existing tools
  ☆13Updated 2 months ago
• RapidResponseBench / rapidresponsebench
  ☆27Updated 3 months ago
• Yu-Fangxu / COLD-Attack
  [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
  ☆134Updated 2 months ago
• wagner-group / prompt-injection-defense
  Fine-tuning base models to build robust task-specific models
  ☆27Updated 10 months ago
• ebagdasa / multimodal_injection
  ☆79Updated last year
• SheltonLiu-N / Universal-Prompt-Injection
  The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".
  ☆40Updated 3 months ago
• NYU-LLM-CTF / nyuctf_agents
  The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench
  ☆49Updated 2 weeks ago
• JosephTLucas / vger
  An interactive CLI application for interacting with authenticated Jupyter instances.
  ☆50Updated 11 months ago
• dreadnode / marque
  Minimal workflows
  ☆15Updated 11 months ago
• ThuCCSLab / JailbreakEval
  [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆110Updated this week
• pasquini-dario / LLMmap
  ☆24Updated 4 months ago
• dreadnode / robopages-cli
  CLI and API server for https://github.com/dreadnode/robopages
  ☆29Updated last week
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆20Updated last year
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆49Updated 6 months ago