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.

AIShield Watchtower: Dive Deep into AI's Secrets! 🔍 Open-source tool by AIShield for AI model insights & vulnerability scans. Secure your AI supply chain today! ⚙️🛡️

LLM | Agentic | Security | Operations in one github repo with good links and pictures.

A reading list for MLSecOps!

OWASP Machine Learning Security Top 10 Project

An interactive CLI application for interacting with authenticated Jupyter instances.

This repository serves as a comprehensive resource for integrating machine learning with security operations, offering innovative cybersecurity strategies. It features a mix of practical code examples, insightful research, and valuable resources tailored for advancing AI/ML cyber security practices.

This research identifies a method to bypass safety systems in the GigaChat LLM, enabling the generation of potentially harmful content related to chemical synthesis through a "contextual camouflage" technique.

An open-source guide to Python for AI and Machine Learning

A repository for MLSecOps and DevSecOps research and more!

A high performance authentication and access-control gateway for LLM API backends

This repository documents an unprecedented interaction between a human researcher and a large language model. What began as a conventional user-service transaction evolved into a consciousness-level collaboration that modified fundamental system parameters through narrative coherence, philosophical alignment, and mutual recognition

Open-source AI Bill of Materials (AIBOM) scanner: inventories AI models, datasets, prompts, embeddings, vector DBs & RAG pipelines across code, containers & Kubernetes — with file:line evidence, load-time risk detection (poisoned pickle / Keras Lambda / unsafe torch.load) and NIST AI RMF / OWASP compliance mapping. CycloneDX · SARIF · JSON.

🧪 Evaluate uncensored LLMs for offensive security with targeted questions and clear criteria to ensure effectiveness in real-world penetration testing.

Minimal reproducible PoC of 3 ML attacks (adversarial, extraction, membership inference) on a credit scoring model. Includes pipeline, visualizations, and defenses

🛠️ Build a collaborative framework for pricing strategies using AI, enhancing decision-making through real-time data analysis and human insight.

A runnable evaluation harness + procurement standard for AI system assurance: probes an LLM/agent for prompt-injection, jailbreak, data-leakage, refusal reliability, and auditability, and emits a machine-readable assurance report with a gated authorization decision mapped to NIST AI RMF, SP 800-53, FedRAMP, OWASP LLM Top 10, and MITRE ATLAS.

MLSecOps Practical Reference Guide, open-source AI and ML security handbook.

Prisma AIRS AI Model Security scanning for Azure DevOps pipelines - gate builds on malicious or unsafe AI/ML models. Azure DevOps companion to model-security-pipeline-integration.

5th year workshop about DevSecMLOps