

NOVA - Claude Code Protection System against prompt injection attacks

Modular security toolkit for autonomous agents providing static analysis, configuration auditing, runtime monitoring, and supply chain verification…

Pre-execution intent verification for AI agents. Audits what your AI is about to do, not what it says. Zero dependencies, deterministic, hash-sealed.

Anticipator is an open-source threat detection platform for multi-agent AI systems.

Simple Anti-cheat library for applications that use C++ on windows. #PastedProtection

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

[NeurIPS 2025] An official source code for paper "GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning".

Detection of rootkit file hiding activities through analysis of shifts in kernel function execution times.

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