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
• dropbox / llm-security
  Dropbox LLM Security research code and results
  ☆250Updated last year
• gdalmau / lakera-gandalf-solutions
  My inputs for the LLM Gandalf made by Lakera
  ☆48Updated 2 years ago
• safellama / plexiglass
  A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
  ☆151Updated 2 years ago
• JosephTLucas / jupysec
  A JupyterLab extension to evaluate the security of your Jupyter environment
  ☆39Updated 2 years 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
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆63Updated 11 months ago
• dreadnode / AIRTBench-Code
  Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
  ☆92Updated this week
• dreadnode / robopages
  A YAML based format for describing tools to LLMs, like man pages but for robots!
  ☆82Updated 8 months ago
• mik0w / pallms
  Payloads for Attacking Large Language Models
  ☆116Updated 7 months ago
• 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
• 5stars217 / offsecml
  source code for the offsecml framework
  ☆46Updated last year
• dreadnode / rigging
  Lightweight LLM Interaction Framework
  ☆402Updated this week
• BishopFox / raink
  Use LLMs for document ranking
  ☆160Updated 8 months ago
• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆117Updated last year
• trailofbits / pajaMAS
  Multi-agent system (MAS) hijacking demos
  ☆39Updated this week
• JosephTLucas / vger
  An interactive CLI application for interacting with authenticated Jupyter instances.
  ☆55Updated 8 months ago
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆68Updated 10 months ago
• moohax / Talks
  Central repo for talks and presentations
  ☆47Updated last year
• subzer0girl2 / AI-Threat-Mind-Map
  ☆44Updated last year
• phreakAI / metasploit-gym
  An environment for testing AI agents against networks using Metasploit.
  ☆45Updated 2 years ago
• cosai-oasis / ws4-secure-design-agentic-systems
  Repository for CoSAI Workstream 4, Secure Design Patterns for Agentic Systems
  ☆45Updated last month
• 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
• pasquini-dario / project_mantis
  Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks
  ☆93Updated 7 months ago
• alkaet / LobotoMl
  LobotoMl is a set of scripts and tools to assess production deployments of ML services
  ☆10Updated 3 years ago
• cosai-oasis / oasis-open-project
  This repository is for administrative documents for the CoSAI OASIS Open Project
  ☆70Updated this week
• Addepar / RedFlag
  RedFlag uses AI to identify high-risk code changes. Run it in batch mode for release candidate testing or in CI pipelines to flag PRs and…
  ☆158Updated last year
• mithril-security / blindbox
  BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps
  ☆63Updated 2 years ago
• google-research / camel-prompt-injection
  Code for the paper "Defeating Prompt Injections by Design"
  ☆205Updated 6 months ago