Alternatives and similar repositories for mlattacks

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

• Reapor-Yurnero / imprompter
  Codebase of https://arxiv.org/abs/2410.14923
  ☆52Updated last year
• safellama / plexiglass
  A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
  ☆151Updated 2 years ago
• gdalmau / lakera-gandalf-solutions
  My inputs for the LLM Gandalf made by Lakera
  ☆48Updated 2 years ago
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆62Updated 11 months ago
• dropbox / llm-security
  Dropbox LLM Security research code and results
  ☆250Updated last year
• mik0w / pallms
  Payloads for Attacking Large Language Models
  ☆116Updated 7 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.
  ☆80Updated last year
• trailofbits / awesome-ml-security
  ☆154Updated 4 months ago
• JosephTLucas / vger
  An interactive CLI application for interacting with authenticated Jupyter instances.
  ☆55Updated 8 months ago
• phreakAI / metasploit-gym
  An environment for testing AI agents against networks using Metasploit.
  ☆45Updated 2 years ago
• dreadnode / rigging
  Lightweight LLM Interaction Framework
  ☆402Updated this week
• 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…
  ☆201Updated 3 months ago
• trailofbits / pajaMAS
  Multi-agent system (MAS) hijacking demos
  ☆39Updated this week
• JosephTLucas / lintML
  A security-first linter for code that shouldn't need linting
  ☆17Updated 2 years ago
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆112Updated last year
• BishopFox / raink
  Use LLMs for document ranking
  ☆160Updated 8 months ago
• JosephTLucas / jupysec
  A JupyterLab extension to evaluate the security of your Jupyter environment
  ☆39Updated 2 years ago
• dreadnode / robopages
  A YAML based format for describing tools to LLMs, like man pages but for robots!
  ☆82Updated 8 months ago
• facebookresearch / privacy_adversarial_framework
  The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspire…
  ☆57Updated 2 years ago
• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆117Updated last year
• 5stars217 / offsecml
  source code for the offsecml framework
  ☆46Updated last year
• google-research / camel-prompt-injection
  Code for the paper "Defeating Prompt Injections by Design"
  ☆205Updated 6 months ago
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆68Updated 10 months ago
• dreadnode / AIRTBench-Code
  Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
  ☆92Updated this week
• StavC / Here-Comes-the-AI-Worm
  Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems
  ☆221Updated 4 months ago
• forcesunseen / llm-hackers-handbook
  A guide to LLM hacking: fundamentals, prompt injection, offense, and defense
  ☆180Updated 2 years ago
• cosai-oasis / ws4-secure-design-agentic-systems
  Repository for CoSAI Workstream 4, Secure Design Patterns for Agentic Systems
  ☆45Updated last month
• pasquini-dario / project_mantis
  Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks
  ☆93Updated 7 months ago
• user1342 / Oversight
  A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.
  ☆54Updated last year
• gradio-app / safehttpx
  ☆71Updated 2 months ago