
SOC-Analyst-Portfolio
A curated portfolio showcasing my SOC investigations, threat hunting projects, DFIR labs, detection engineering, technical blogs, and cybersecurity…

A curated portfolio showcasing my SOC investigations, threat hunting projects, DFIR labs, detection engineering, technical blogs, and cybersecurity…

AST-based Static Code Analyzer with Agentic LLM-Powered Relationship Mapping to discover Python RCE paths and deep deserialization chains on AI, LLM,…

An implementation of the FAIR CRQ Framework

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

Memory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…

An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.

Training-free anomaly detection framework using Shannon Entropy, Fisher Information, and Wasserstein Distance to map system states into geometrically…

Is 4-bit quantization more than noise to a chat model's safety behaviour? Code, pre-registration and labels.

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

NVR with realtime local object detection for IP cameras

A privacy-first app that strips AI watermarks from content you own.

Local-first, continuous screen and audio recorder with AI-powered search, transcription, and automation. Captures everything you see, say, and do,…

Fast and accurate AI powered file content types detection

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine…

A python library for user-friendly forecasting and anomaly detection on time series.

MCP Server for Ghidra

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