
adversarial-robustness-toolbox
Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

Open-source email filtering framework that detects spam and phishing using content analysis, header checks, Bayesian scoring, and DNS blocklists.

Open source entropy based invalid traffic detection and pre-bid filtering.

Open Source Deep Packet Inspection Software Toolkit

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Streaming machine learning library for incremental learning on data streams, providing online estimators, drift and anomaly detection, pipelines,…

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

Re-play Security Events

ML-driven threat detection and continuous monitoring platform built for federal zero trust architectures.

DGA Domain Detection using Bigram Frequency Analysis

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

NVR with realtime local object detection for IP cameras

A python library for user-friendly forecasting and anomaly detection on time series.

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

Detects unknown jailbreak attacks in large vision-language models using hidden state analysis and autoencoders, with training and evaluation…

This repository includes the source code used in the "Characterization and Detection of Cross-Router Covert Channels" paper.

Algorithms for outlier, adversarial and drift detection