Heimdall-SecurityV2 is a DevSecOps security validation framework that combines Semgrep SAST, LLM-based exploitability reasoning, safe DAST validation, and CI/CD policy reporting to reduce false positives.

GUARDIUM is an intelligent Wazuh rule optimization framework designed to reduce false positives, improve alert accuracy, and assist SOC teams in maintaining high-quality SIEM detections. GUARDIUM combines rule analysis, threat context, and Large Language Models (LLMs) to automatically evaluate, explain, and optimize Wazuh rules.

A context-aware Python secret scanner that reduces false positives using entropy, path, and keyword analysis — benchmarked with ~95% noise reduction across major open-source repos.

Python security gate with intelligent ML scoring that reduces false positives by 95%. Orchestrates Bandit, pip-audit, and Semgrep into a unified CI/CD pipeline. Includes baseline management, policy enforcement, and explainable predictions. Production-ready with comprehensive tests.

This repository contains the code for using the Negative Sigmoid loss, a deep learning loss function designed to penalize false positive segmentations in negative patches

Memory-augmented SOC alert-triage research prototype with reproducible CIC-IDS2017 validation, leakage-aware controls, and publication-ready figures.