
Exponentiated-Gradient-Descent-LLM-Attack
A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

Advanced detection of port scanning, DoS and malware attacks using Machine Learning techniques

Research toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…

AI 驱动的 SOC 仿真平台

An automated, high-precision zero-shot evaluation pipeline for OpenAI's CLIP model on CIFAR-10. Features 88.80% accuracy, Safetensors security…

Hide valuable information where it's least expected

Multi-engine framework for unpacking and analyzing VM-protected binaries using dynamic taint tracking, symbolic execution, pattern classification,…

Embedded GRU neural network for real-time human behavior verification via mouse movement analysis, detecting automated analysis systems, sandboxes,…

A web-based tool to assist the work of the intuitive threat analysts.

Restructured and Collaborated SIEM and CVSS Infrastructure. Presented at Blackhat Asia Arsenal 2020.

Automating Host Exploitation with AI

Re-play Security Events

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

This project (PoC for now, and part of Shit Bucket) involves face detection, face recognition and adversarial input to protect avatars