Real-time eBPF-powered network security monitor with AI-driven threat detection. Surfaces port scans, DDoS attacks, botnet activity, and anomalies at 100Gbps+ speeds with sub-microsecond latency (~150 million packets/sec).

Behavioral Fingerprinting-Augmented Embedded IDS on Raspberry Pi 4 + ESP32. Detects zero-day attacks by learning per-device traffic profiles using Isolation Forest; no signatures needed. Features distributed MQTT nodes, real-time Flask dashboard, iptables auto-blocking, and GPIO alerts.

This repository is dedicated to our source code for our research paper titled Synthetic Malware Image Generation Based on Generative Models Against Zero-Day Attacks. We presented our research work at the Silicon Valley Cybersecurity Conference 2025.

AI-powered Network Intrusion Detection System achieving 99.1% validation accuracy using a 10-model ML ensemble (XGBoost, LSTM, GNN, Autoencoder) with explainable AI (SHAP), real-time threat detection, SOC-style dashboard, automated response, and secure Azure CI/CD deployment.

SHAP-Explained Agentic IDS: A 3-layer cybersecurity NIDS combining Random Forest, SHAP TreeExplainer, LangGraph Multi-Agent reasoning, and MART red-teaming.

Wraith is a low-level Rust security sensor that answers a question most tools can't: "is this process being exploited right now?" By focusing entirely on anomalous runtime behavior rather than known signatures or payloads, Wraith detects live exploits and uncovers zero-day vulnerabilities completely in advance of a patch.

🛡 ThreatSense — Detects social engineering cyber attacks by analyzing emotional manipulation patterns (fear, urgency, authority, greed) in messages. Rule-based scoring + ML ensemble (93.3% accuracy). Built with Python, scikit-learn & Streamlit. Third Year MiniProject — CSE 2025–26.

An enterprise-grade IoT SIEM dashboard using unsupervised machine learning to detect thermal and power anomalies. Developed for my BSc IT Honors Research capstone.

Hybrid Transformer–BiLSTM framework for Zero-Day intrusion detection, Open-Set Recognition, and Self-Supervised Cyber Threat Intelligence.

Hyperdimensional Intrusion Detection System for Zero-Day Exploit detection in encrypted traffic using Conformal Geometric Algebra, online learning, and real-time anomaly scoring.

SentinAI is an anomaly-based Network Intrusion Detection System that uses XGBoost trained on CICIDS-2017 to detect DDoS, port scans, and unknown threats by learning normal traffic behavior — achieving F1: 1.0000. Includes a real-time SOC dashboard, rule-based incident response, and live Kali Linux attack validation.

Open-set zero-day malware detection from decompiled binary graph structure. Leakage-free leave-one-family-out evaluation with conformal thresholds, cross-decompiler ensembling, and OOD-gated knowledge memory for emerging family discovery.

Behaviour-First Zero-Day Detector (BFZDD) An AI-powered malware detector that learns normal program behaviour using LSTM/GRU/Transformer autoencoders and flags anomalies in real time — enabling true zero-day detection beyond signatures. Includes live trace analysis, fine-tuning UI, model versioning, and event heatmaps.

EvoIDS is a self-evolving intrusion detection system that detects concept drift, adapts to changing network traffic patterns, and identifies zero-day attacks using a multi-detector open-set recognition framework.

Hybrid AI-powered Intrusion Detection System (NIDS) combining 1D-CNN & Variational Autoencoder (VAE) to detect known cyberattacks and zero-day anomalies. Features a premium Streamlit "Command Center" dashboard for real-time network traffic analysis.

SentinelX is an AI-assisted Security Operations Center (SOC) for advanced threat detection, real-time security monitoring, intelligent incident investigation, and ML-based zero-day attack detection.

SentinAI is an anomaly-based Network Intrusion Detection System that uses XGBoost trained on CICIDS-2017 to detect DDoS, port scans, and unknown threats by learning normal traffic behavior — achieving F1: 1.0000. Includes a real-time SOC dashboard, rule-based incident response, and live Kali Linux attack validation.