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

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

Blazing-Fast Token-Efficient Intrusion Detection System (IDS) based on TypeSafe's Jev.

Runtime Application Self Protection for Python web servers, serverless functions and MCP servers, detecting attacks, prompt injection and data leaks…

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

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

Automatic extraction of relevant features from time series:

Reverse Shell Detection with Machine Learning

Lightweight Python-based IDS that monitors network traffic in real-time using Scapy, detecting DoS/DDoS attacks via per-IP request rate analysis with…

A Zeek based Mitre Caldera detector.

A Zeek based AsyncRAT malware detector.

Graph-based insider threat detection using GCN-BiLSTM and attention models on CMU CERT datasets. Includes data preprocessing, feature extraction, and…

A Zeek OSPF packet analyzer based on Spicy.

First iteration of ML based Feedback WAF

ETW based POC to identify direct and indirect syscalls

A machine learning toolkit for log-based anomaly detection [ISSRE'16]

A deep learning toolkit for log-based anomaly detection

CVE-2020-9483 OR CVE-2020-13921

A package for capturing and analyzing network flow data and intraflow data, for network research, forensics, and security monitoring.