awesome-mlsecops
github.com/riccardobiosas/awesome-mlsecops ↗A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me rogue agents and autonomous agent security resources from awesome-mlsecops"
Installation instructions →What's inside
Open Source Security Tools
- AdrianRogue Agents and Autonomous Agent Security
Apache-2.0 runtime monitoring and control engine that judges an agent's tool calls, outputs, and reasoning traces against its declared remit to detect misaligned, off-policy, or out-of-remit behaviour and block or hold actions in flight, with self-hosted deployment and SDKs for LangChain, Anthropic, TypeScript, and Claude Code
- AdvBoxAdditional Open-Source Tools
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow
- Adversarial Machine Learning CTFAdditional Open-Source Tools
CTF challenge demonstrating adversarial-image attacks against neural-network image classifiers
- Adversarial Robustness ToolboxAdversarial Machine Learning Testing
Library of defense methods for ML models against adversarial attacks
- AdvertorchAdditional Open-Source Tools
Python toolbox for adversarial robustness research
- Agent Governance ToolkitRogue Agents and Autonomous Agent Security
MIT-licensed Microsoft toolkit, in public preview, that intercepts every agent tool call, message, and delegation in deterministic code against a YAML policy, adds per-agent identity, sandboxing, and tamper-evident audit trails, and maps its controls to all ten OWASP Agentic Top 10 risks including ASI10 rogue agents
Books
Adversarial Machine Learning Research Repositories
- Adversarial-Attacks-with-Relativistic-AdvGAN
Adversarial example generation
- AgentPoison
LLM agent backdoor poisoning
- backdoor
Backdoor attacks
- BlindMI
Membership inference attacks
- Class_Activation_Mapping_Ensemble_Attack
Adversarial evasion attacks
- COLD-Attack
Adversarial optimization attacks
Attack Vectors
Blogs and Publications
- Adversarial Prompts Engineering
- Agentic Misalignment: How LLMs Could Be Insider Threats
- AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
- Audio-jacking: Using generative AI to distort live audio transactions
- CircleGuardBench: New Standard for Evaluating AI Moderation Models
- DreadNode Paper Stack
AI Security and MLSecOps Beginner Resources
- AI Risk Assessment for ML Engineers
- AI Security 101
- Microsoft AI Red Team
- Microsoft - Generative AI Security for Beginners
Generative AI Security for Beginners
Community Resources
The MLSecOps Hacker Newsletter
Showing a sample of 199 resources. View the full list on GitHub →