
alibi-detect
Algorithms for outlier, adversarial and drift detection

Algorithms for outlier, adversarial and drift detection

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine…

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

Self-referenced local contrast for knowledge-poison detection in retrieval-augmented generation

Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

Reverse Shell Detection with Machine Learning

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

A Red Team vs. Blue Team Adversarial AI Simulation.

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