
BrokenHill
A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

N-gram-based type recovery tool for binaries, recovering structures and function signatures from decompiled code with high throughput and actionable…

A network packet forensics tool for SSH

Air-gapped cybersecurity assistant for security professionals. 100% offline AI-powered analysis tool for Nmap, Volatility, BloodHound, Metasploit,…

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks. Red Team AI Benchmark is a CLI model-evaluation benchmark. It…

image scaling attacks for multi-modal prompt injection

Automated steganography detection tool that scans websites, web servers, and local directories using AI-driven object/text recognition and deep file…

Open-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…

Malware detection using learning and information retrieval for Android

FARO - Document Sensitivity Detector

Extracts structured Cyber Threat Intelligence (CTI) from PDF, DOCX, and TXT documents using LLMs. Generates MITRE ATT&CK attack flows, detection…

Python library for local LLM-powered security analysis with Ghidra binary analysis, C/C++ vulnerability scanning, and MCP tool integration for…

Spam Scanner is a Node.js anti-spam, email filtering, and phishing prevention tool and service. Built for @ladjs, @forwardemail, @cabinjs, @breejs,…


Droidefense: Advance Android Malware Analysis Framework

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

This tool parses log data and allows to define analysis pipelines for anomaly detection. It was designed to run the analysis with limited resources…

Machine-learn password mangling rules