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.

owasp threat-modeling ai-agents adversarial-machine-learning machine-learning-security ai-security mlops supply-chain-security data-poisoning ai-governance mlsecops large-language-model prompt-injection llm-security ai-red-teaming mcp-security rag-security model-poisoning mlops-security agentic-security

• Updated Nov 9, 2026
• Astro

Simple pytorch implementation of FGSM and I-FGSM

adversarial-example adversarial-attacks machine-learning-security

• Updated Mar 21, 2018
• Python

Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.

machine-learning ai penetration-testing ctf offensive-security adversarial-machine-learning machine-learning-security large-language-models aisecurity vulnerable-llm-application

• Updated May 13, 2026
• Python

pretrained BERT model for cyber security text, learned CyberSecurity Knowledge

nlp security apt transformers cybersecurity attention threat-hunting deeplearning cyber-security nlp-machine-learning bert threat-analysis security-automation threat-intelligence machine-learning-security cyber-threat-intelligence threat-detection transformer-encoder bert-embeddings deep-learning-security

• Updated Apr 28, 2023
• Python

Code for our USENIX Security 2021 paper -- CADE: Detecting and Explaining Concept Drift Samples for Security Applications

machine-learning tensorflow keras artificial-intelligence ids autoencoder mlp explanation concept-drift interpretability explainable-ai explainable-ml xai machine-learning-security drebin self-supervised-learning contrastive-learning ids2018

• Updated Mar 25, 2023
• Python

Reading list for adversarial perspective and robustness in deep reinforcement learning.

deep-reinforcement-learning ai-safety machine-learning-security ai-security robust-machine-learning ai-alignment safe-reinforcement-learning robust-reinforcement-learning responsible-ai adversarial-reinforcement-learning secure-ai ml-security llm-security reinforcement-learning-safety llm-safety artificial-intelligence-security artificial-intelligence-alignment robust-deep-reinforcement-learning reinforcement-learning-security large-language-model-safety

• Updated Mar 2, 2026

Adversarial Machine Learning (AML) Capture the Flag (CTF)

data-science machine-learning artificial-intelligence cybersecurity infosec ctf adversarial-machine-learning machine-learning-security

• Updated Mar 14, 2024
• Jupyter Notebook

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data Poisoning, PII, and Prompt Injections. Secure your AI Supply Chain.

static-analysis jupyter-notebook ci-cd pytorch devsecops data-security machine-learning-security ai-security mlops sbom huggingface pii-detection supply-chain-security cosign sigstore generative-ai prompt-injection llm-security rag-security pickle-security

• Updated Aug 4, 2026
• Python

Static security scanner for ML model files — detects pickle bombs, Keras Lambda RCE and GGUF template injection, and generates CycloneDX / SPDX AI-BOMs (AIBOM) as EU AI Act, CRA and FDA §524B evidence.

pytorch spdx cra malware-detection machine-learning-security ai-security mlops sbom cyclonedx huggingface supply-chain-security mlsecops llm-security mlbom ai-bom aibom cyclonedx-sbom eu-ai-act cyber-resilience-act model-scanning

• Updated Nov 8, 2026
• Python

Train AI (Keras + Tensorflow) to defend apps with Django REST Framework + Celery + Swagger + JWT - deploys to Kubernetes and OpenShift Container Platform

machine-learning jwt deep-neural-networks ai openshift tensorflow rest-api django-rest-framework swagger drf keras celery network-analysis network-security celery-tasks machine-learning-security ai-security anti-nex

• Updated Nov 2, 2018
• Python

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

cybersecurity openai ai-safety adversarial-attacks machine-learning-security ai-security content-moderation guardrails responsible-ai pii-detection llm prompt-engineering generative-ai chatgpt prompt-injection llm-security ai-gateway hallucination-detection llm-observability ai-firewall

• Updated Nov 12, 2026

Do you want to learn AI Security but don't know where to start ? Take a look at this map.

map owasp machine-learning-security ai-security llm ml-security

• Updated Apr 23, 2024

Hands-on lessons for attacking and defending AI systems, starting with the OWASP Top 10 for LLM Applications.

docker owasp ethical-hacking adversarial-attacks machine-learning-security ai-security cybersecurity-education prompt-injection llm-security

• Updated Jun 22, 2025
• Python

Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)

machine-learning privacy deep-neural-networks entropy deep-learning information-theory pytorch data-privacy mutual-information adversarial-machine-learning celeba-dataset machine-learning-security utkface

• Updated Jan 11, 2023
• Python

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.

game python cli owasp cybersecurity penetration-testing gamification ctf capture-the-flag security-training red-team machine-learning-security ai-security prompt-injection llm-security adversarial-ai

• Updated Mar 19, 2026
• Python

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial attacks with a web-based interactive lab.

react docker kubernetes jailbreak model-alignment machine-learning-security ai-security fastapi huggingface prompt-injection llm-security llm-safety security-research-tool ai-evaluation-framework adversarial-ai prompt-defense llm-red-teaming

• Updated Mar 27, 2026
• Python

Free prompt injection CTF: 16 LLM security missions plus a 30-mission Agentic Security Lab (OWASP Agentic Top 10), defender mode, optional live-model grading. No signup.

firebase typescript nextjs jailbreak owasp ctf jailbreaking ai-safety ai-agents red-teaming machine-learning-security ai-security mlsecops prompt-injection llm-security agentic-ai

• Updated Nov 12, 2026
• HTML

A curated bilingual list of cryptanalytic neural-network model extraction papers, code, taxonomies, and open problems.

cryptanalysis neural-networks awesome-list model-extraction machine-learning-security hard-label model-stealing cryptanalytic-extraction

• Updated Nov 11, 2026
• Python

Datasets for training deep neural networks to defend software applications

react flask machine-learning django deep-neural-networks ai spring vue tensorflow rest-api keras react-redux open-data deeplearning keras-neural-networks network-security tensorflow-models machine-learning-security ai-security anti-nex

• Updated Jun 4, 2018
• Python

Comprehensive, auto-updating literature review of GenAI & LLM security research, standards, tools, and resources. 100+ curated entries with interactive webapp.

owasp cybersecurity jailbreaking ai-safety literature-review red-teaming machine-learning-security ai-security adversarial-ml mitre-atlas prompt-injection llm-security genai-security agentic-ai nist-ai-rmf

• Updated Nov 9, 2026
• Python