A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.

Simple pytorch implementation of FGSM and I-FGSM

pretrained BERT model for cyber security text, learned CyberSecurity Knowledge

CTF challenges designed and implemented in machine learning applications

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

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

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

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

AI SBOM: AI Software Bill of Materials - The Supply Chain for Artificial Intelligence

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.

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

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

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

Datasets for training deep neural networks to defend software applications

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

Summary of the presentation on Real and Stealthy Attacks on State-of-the-Art Face Recognition Systems at the Seminar: Machine Learning in Cyber-security at FU Berlin

Systematic Security Evaluation Framework for AI Coding Assistants - Detection of prompt injection vulnerabilities

Educational research demonstrating weight manipulation attacks in SafeTensors models. Proves format validation alone is insufficient for AI model security.

Understanding Adversarial Attacks Through MNIST

Build an AI Security Analyst Assistant with RAG! LEARN FROM SCRATCH

Final Year Thesis Project (COMP4981H) for Computer Science Students in HKUST

Awesome-DL-Security-and-Privacy-Papers

Adversarial perturbation intensity strategy achieving chosen intra-technique transferability level for logistic regression

A stochastic input pre-processing technique based on a process of down-sampling/up-sampling using convolution and transposed convolution layers. Defending convolutional neural network against adversarial attacks.

Security Vulnerabilities and Defensive Mechanisms in CLI/Terminal-Based Large Language Model Deployments - A Comprehensive Research Synthesis (Technical Report, November 2025)

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis

No description provided.

Detect and defend against adversarial attacks on ML models

CISPA European Championship 2026 — 3-task ML security hackathon: black-box image reconstruction, generative model fingerprinting, and hardware-dependent chimera generation.

This is the repository for Homeworks of COMP 530 Data Privacy and Security course given by Emre Gursoy at Koc University.