
LeakGauge
Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
ML-based security tools, adversarial machine learning, and AI-powered cyber defense.

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
A curated portfolio showcasing my SOC investigations, threat hunting projects, DFIR labs, detection engineering, technical blogs, and cybersecurity…

Reconstructs legacy Windows binaries into C source by pairing Ghidra decompiler exports with local LLMs, producing compile-checked candidates and…

Local white-box gradient attacks for open-weight LLMs: GCG/PEZ suffix search, layer saliency, weight snapshots, and rank-1 suffix-to-delta fitting…

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

Android Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware

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

Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD

Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation.…

Customer Assurance Operating System. Answer the security questionnaires your customers send you, once.

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Hunting for passwords with deep learning

ML-based detection of Zombie ZIP archive header evasion attacks (CVE-2026-0866)

A Binary Genetic Traits Lexer Framework

A Ghidra plugin for locating object file boundaries.

LLM powered fuzzing via OSS-Fuzz.
