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

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


Framework for implementing Network Intrusion Detection Systems (NIDS) aimed at identifying anomalies in network flows using Federated Learning models.

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

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


LLM-agent-powered concolic execution engine that instruments source code, summarizes path constraints in natural language, and generates test cases…

Decentralized Autonomous Research Collective. Lean 4-verified, IPFS-backed, agent-native. Production paper: arXiv:2604.19792. Live at p2pclaw.com.

Automated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…

Stalk your Friends. Find their Instagram, FB and Twitter Profiles using Image Recognition and Reverse Image Search.

Restructured and Collaborated SIEM and CVSS Infrastructure. Presented at Blackhat Asia Arsenal 2020.