


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

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

image scaling attacks for multi-modal prompt injection

Fast and accurate AI powered file content types detection

Static analysis of malicious Python code

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

SAFE embeddings to match functions in yara

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

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

A network packet forensics tool for SSH

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

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

ML-assisted forensic analysis tool that automates memory, disk, and live system triage on Windows using Volatility 3, autorunsc, and sigcheck to…