Build AI-powered security tools. 50+ hands-on labs covering ML, LLMs, RAG, threat detection, DFIR, and red teaming. Includes Colab notebooks, Docker environment, and CTF challenges.

Noise Injection Techniques provides a comprehensive exploration of methods to make machine learning models more robust to real-world bad data. This repository explains and demonstrates Gaussian noise, dropout, mixup, masking, adversarial noise, and label smoothing, with intuitive explanations, theory, and practical code examples.

Comprehensive taxonomy of AI security vulnerabilities, LLM adversarial attacks, prompt injection techniques, and machine learning security research. Covers 71+ attack vectors including model poisoning, agentic AI exploits, and privacy breaches.

Complete 90-day learning path for AI security: ML fundamentals → LLM internals → AI threats → Detection engineering. Built from first principles with NumPy implementations, Jupyter notebooks, and production-ready detection systems.

An application to demonstrate stealing an AI model through knowledge distillation.

This project aims to address this gap by conducting a systematic, controlled study of human versus LLM-generated text detectability using paired question–answer datasets. Rather than proposing a novel detection architecture, the focus is on analyzing detection robustness, failure modes, and the impact of adversarial humanization strategies.

🤖 Test and secure AI systems with advanced techniques for Large Language Models, including jailbreaks and automated vulnerability scanners.

A curated list of awesome AI security tools, frameworks, and resources. OWASP AI Testing Guide, Agentic AI Top 10, EU AI Act, adversarial ML, LLM red-teaming, prompt injection.

A collection of resources documenting my research and learning journey in AI System Security.

🛡️ Discover and analyze critical vulnerabilities in Meta AI's Instagram Group Chat, ensuring robust security through comprehensive testing and reporting.

Bug bounty report demonstrating prompt injection and command execution vulnerabilities in Meta AI's Instagram Group Chat

From the first artificial neurons to autonomous defense systems — Book + Labs + Papers on AI history, neural networks, adversarial ML, and The Warden architecture. By Daniel Dieser.

Collection of Python security analysis tools for ML models and infrastructure. Includes FGSM harness, model inspection, poison monitoring, and deployment security validation.

Reproducible security benchmarking for the Deconvolute SDK and AI system integrity against adversarial attacks.

Mechanism-grounded taxonomy of 40 LLM jailbreak patterns across 10 categories. Full evaluation harness for 4 frontier models. AI safety research with responsible disclosure.

Master's students in NCCU SoSLab maintaining a cleaned and restructured version of INCITE (based on PyCT).

Tools for generating adversarial images that expose vulnerabilities in multimodal LLMs. Typographic, perturbation, steganographic, and visual injection attacks.

FP-16: Verified Delegation Protocol for Multi-Agent Systems — LLM-as-judge + crypto signing + adaptive rate limiting

A curated list of awesome resources for AI system security.

SR 11-7 & EU AI Act compliant LLM validation framework for financial services — accuracy, adversarial robustness, and explainability auditing with automated report generation.