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

Two-layer LLM firewall that blocks prompt-injection inputs via regex rules plus a Gemini classifier, and catches secret or system-prompt leaks in bot…

Kernel-level security & attack response for Linux servers.

An audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…

Java library to analyse Portable Executable files with a special focus on malware analysis and PE malformation robustness

Runtime guard skill that detects and blocks malicious skill-induced attacks in skill-augmented agents, with an MCTS loop that evolves the guard…

Maliciousness scoring for Linux commands

Reproducible Colab pipeline that grounds six AI Security Literacy competency dimensions in public benchmarks and survey microdata, producing figures,…

eBPF-based Linux rootkit detector using multi-channel cross-view analysis (sched_switch, NMI, /proc) to detect DKOM, tracepoint tampering, and…

OSINT - Data Visualization - Blockchain - Awareness - Scam

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

Reverse-proxy web application firewall with WAF, anti-bot and anti-DDoS protection at L3/L4/L7, custom rules, rate limiting, geo/IP filtering and…

Powerful protection for AI agents - Open-source security and cost tracking for AI applications

Simulation code and results for a private, verifiable, Byzantine-robust federated intrusion detection protocol using secret sharing, Merkle audits…

Kratos Minifilter is a Windows kernel driver (FLTMGR.SYS) built for real-time ransomware detection and file I/O mitigation. It intercepts low-level…

Zero-Trust Cellular Defense Sub-Service for Android (IMSI-Catcher, 2G SMS Blaster, and 4G aLTEr Detection & Safe Routing)

ML-Based behavioral endpoint detection system for Linux machines

Reference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…

My experiments in weaponizing ONOS applications (https://github.com/opennetworkinglab/onos)