mlsecurity

OWASP Machine Learning Security Top 10 Project

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

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.

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

Zero Trust AI 360

ONNX-Stego is a Python proof-of-concept for hiding short authenticated messages inside float32 ONNX model weights. It embeds bits in the least significant mantissa bit of selected weights, while using modern authenticated encryption for the hidden payload.

Global mesh network with distributed MLS encrypted VLANs trunking

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

MLSecOps in Action; From Foundations to Applied Security

Package for security in machine learning. Contains known algorithms for adversarial attacks and defenses.

list of resources for AI/ML/LLM security

A comprehensive, beginner-to-advanced Machine Learning Security (ML-Sec) self-study course covering adversarial machine learning, data poisoning, evasion attacks, model privacy, robustness, secure ML pipelines, AI/LLM security, and defensive techniques. Includes practical Python labs, real-world security scenarios, hands-on projects.

Bert models interpretation and security checker

The practical code of Machine Learning and Security course lab

A CRAG agent crafted using Gemini, langgraph and python to audit the ML scripts before deploying in production level

This research exploring [Research Idea in a few words]. This work [Specific benefit of research] holds promise for [Positive impact].

This research explores a novel targeted attack for neural network classifiers. This research has been led by Dr.Samer Khamaiseh with ongoing efforts of Deirdre Jost and Steven Chiacchira

The reCAPTCHAv2 solving challenge