
SuperDiagnosticTool
AI-powered Windows diagnostic & auto-repair tool using Google Gemini. Detect crashes, optimize performance, scan for malware, and generate PowerShell…

AI-powered Windows diagnostic & auto-repair tool using Google Gemini. Detect crashes, optimize performance, scan for malware, and generate PowerShell…

Linux system-call monitor using ptrace to trace file, process, network, and memory activity, with namespace isolation and machine learning…

An interactive CLI application for interacting with authenticated Jupyter instances.

NotebookLM on steroids — purpose-built for security researchers.

VEDAS-Driven Autonomous Generation of Suricata Rules for CVEs

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

A serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks

Graph-based threat detection system using inexact graph vector matching to compare threat graphs with CTI-derived attack query graphs for automated…

Implementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

Multi-format malware analysis platform combining a stealth Ring-3 Windows sandbox, static PE/PDF analyzers, ransomware key recovery, and an AI…

Robust audio watermarking framework embedding binary messages into magnitude spectrograms, with differentiable attack simulation, Q-Former pooling,…

Inference scaling for LLM safety assurance

ML-Based behavioral endpoint detection system for Linux machines

Proof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…

A next-generation multi-echelon anti-ransomware fortress for Windows, combining hypervisor, eBPF, AI deception, and hardware-enforced security.

Stop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…

Adversary-resilient deep learning architecture for secure 5G indoor localization, combining CNN and multi-head attention to defend against signal…