#1Behavioral anomaly detection, outlier analysis, UEBA, and statistical threat detection tools.
Kitploit recommended

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

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.

Linux kernel module using Kprobes to detect and neutralize CVE-2024-1086 heap double-free exploits via temporal gap tracking and active register…

Cross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Offline-first network investigation and response platform for Windows. Turns a pcap or live capture into a full forensic verdict — attack story,…

An event-driven network monitoring platform that performs live packet capture (Npcap), low-latency traffic analytics, and unsupervised threat…

PETriage: A symbol-unified PE file reader for triage, built for multi-platform and multi-interface use.

Benchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.

AI-driven endpoint governance platform that monitors software usage, applies deterministic policy-based risk classification, and generates structured…

3D multi-domain tactical intelligence map — live ships, flights, satellites, cables & space weather in the browser. Time scrubbing, scenario replay,…

NFStream: a Flexible Network Data Analysis Framework.

Hybrid machine-learning pipelines for detecting SQL injection in web traffic, combining DistilBERT and BERT-GNN models with adversarial training and…

Sigma detection rules for AI agent security monitoring

Single-host runtime-security dashboard on eBPF — Go agent + SvelteKit. Live process tree, network map, and rule-based alerts for plain Linux hosts.

ShellSweeping the evil.

This repository hosts a multimodal web attack dataset (MWAD) to advance AI-driven threat detection research.