Alternatives and similar repositories for mlattacks

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

• safellama / plexiglass
  A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
  ☆142Updated last year
• Reapor-Yurnero / imprompter
  Codebase of https://arxiv.org/abs/2410.14923
  ☆49Updated 9 months ago
• dreadnode / rigging
  Lightweight LLM Interaction Framework
  ☆313Updated this week
• JosephTLucas / jupysec
  A JupyterLab extension to evaluate the security of your Jupyter environment
  ☆39Updated 2 years ago
• JosephTLucas / vger
  An interactive CLI application for interacting with authenticated Jupyter instances.
  ☆53Updated 3 months ago
• BishopFox / raink
  Use LLMs for document ranking
  ☆145Updated 3 months ago
• JosephTLucas / lintML
  A security-first linter for code that shouldn't need linting
  ☆16Updated last year
• gdalmau / lakera-gandalf-solutions
  My inputs for the LLM Gandalf made by Lakera
  ☆46Updated last year
• dropbox / llm-security
  Dropbox LLM Security research code and results
  ☆232Updated last year
• moohax / Talks
  Central repo for talks and presentations
  ☆46Updated last year
• sshh12 / llm_backdoor
  Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to pote…
  ☆179Updated 4 months ago
• jaschadub / VectorSmuggle
  Testing platform for covert data exfiltration techniques where sensitive documents are embedded into vector representations and tunneled …
  ☆66Updated last month
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆113Updated last year
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆57Updated 6 months ago
• mithril-security / blindbox
  BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps
  ☆60Updated last year
• gradio-app / safehttpx
  ☆70Updated last month
• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆114Updated last year
• user1342 / Oversight
  A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.
  ☆48Updated 9 months ago
• trailofbits / awesome-ml-security
  ☆139Updated 2 months ago
• dreadnode / robopages
  A YAML based format for describing tools to LLMs, like man pages but for robots!
  ☆75Updated 3 months ago
• mik0w / pallms
  Payloads for Attacking Large Language Models
  ☆92Updated 2 months ago
• StavC / ComPromptMized
  ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications
  ☆203Updated last year
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆65Updated 5 months ago
• zmre / awesome-security-for-ai
  Awesome products for securing AI systems includes open source and commercial options and an infographic licensed CC-BY-SA-4.0.
  ☆65Updated last year
• 5stars217 / offsecml
  source code for the offsecml framework
  ☆41Updated last year
• 5stars217 / malicious_models
  using ML models for red teaming
  ☆43Updated 2 years ago
• google-research / camel-prompt-injection
  Code for the paper "Defeating Prompt Injections by Design"
  ☆64Updated last month
• ucsb-seclab / chainreactor
  ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. T…
  ☆50Updated 9 months ago
• forcesunseen / netsec-goggle
  High signal information security sources Goggle.
  ☆67Updated 2 years ago
• ReversecLabs / llm-vulnerable-recruitment-app
  An example vulnerable app that integrates an LLM
  ☆23Updated last year