Alternatives and similar repositories for research

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

• vinusankars / BEAST
  Implementation of BEAST adversarial attack for language models (ICML 2024)
  ☆88Updated last year
• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆111Updated last year
• pasquini-dario / LLMmap
  ☆48Updated 9 months ago
• RenatoGeh / advtok
  Adversarial Tokenization
  ☆23Updated 2 months ago
• BishopFox / BrokenHill
  A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)
  ☆122Updated 6 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…
  ☆42Updated 5 months ago
• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆75Updated 7 months ago
• NickNameInvalid / LLM_CTF
  ☆65Updated 5 months ago
• ebagdasa / multimodal_injection
  ☆91Updated last year
• PalisadeResearch / intercode
  https://arxiv.org/abs/2412.02776
  ☆59Updated 7 months ago
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆63Updated 4 months ago
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆23Updated last year
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆51Updated 11 months ago
• wagner-group / prompt-injection-defense
  Fine-tuning base models to build robust task-specific models
  ☆31Updated last year
• parameterlab / trap
  Source code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)
  ☆12Updated 7 months ago
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆57Updated 5 months ago
• uiuc-kang-lab / InjecAgent
  ☆67Updated last year
• 5stars217 / malicious_models
  using ML models for red teaming
  ☆43Updated last year
• xsankar / AI-Red-Teaming
  All things specific to LLM Red Teaming Generative AI
  ☆27Updated 8 months ago
• dreadnode / robopages
  A YAML based format for describing tools to LLMs, like man pages but for robots!
  ☆75Updated 2 months ago
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆125Updated last month
• lakeraai / pint-benchmark
  A benchmark for prompt injection detection systems.
  ☆122Updated 2 months ago
• humane-intelligence / ai_village_defcon_grt_data
  ☆14Updated last year
• 5stars217 / offsecml
  source code for the offsecml framework
  ☆41Updated 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".
  ☆51Updated 8 months ago
• bsinger98 / Incalmo
  ☆41Updated this week
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆112Updated last year
• RapidResponseBench / rapidresponsebench
  ☆34Updated 8 months ago
• mik0w / pallms
  Payloads for Attacking Large Language Models
  ☆91Updated last month
• NetSPI / Open-LLM-Security-Benchmark
  ☆15Updated 7 months ago