Awesome MLSecOps: Machine Learning and AI Security Resources
A curated catalog of open-source and commercial MLSecOps tools and resources for securing machine learning models, MLOps pipelines, LLM applications and AI agents, alongside adversarial ML research and threat-modeling material.
MLSecOps is defined here as integrating security throughout the machine learning lifecycle, from data collection and model development through deployment, monitoring and incident response, applying security testing, threat modeling, supply-chain protection, access controls and continuous monitoring. The catalog is aimed at security engineers, ML practitioners, developers and AI red teams.
Sections cover open-source and commercial security tools, data privacy and anonymization tools, ML code security, beginner resources, threat modeling, attack vectors, MLOps infrastructure vulnerabilities, adversarial machine learning research repositories, blogs, publications and books, organized under headings such as model and artifact security for detecting unsafe serialization and malicious payloads.
It is maintained by the author of a related newsletter on AI security for engineers, which covers model supply-chain security, prompt injection, and agent and MCP security topics as new material for the catalog is found.