Nitzan Farhi Shahar, PhD

Nitzan Farhi Shahar, PhD

Senior Vulnerability Researcher & Security Research Lead · PhD in EE (Tel Aviv University)

Senior Vulnerability Researcher & Security Research Lead

I research vulnerabilities, reverse engineer complex systems, and build practical security research tools. My work spans vulnerability research, exploit development, low-level systems, and applied machine learning for cybersecurity.

Publications Projects Datasets GitHub Google Scholar LinkedIn Email

Research & Expertise

  • Vulnerability Research & Reverse Engineering: In-depth binary analysis, protocol reverse engineering, firmware auditing, and discovering security vulnerabilities in complex proprietary software.
  • Exploit Development & Low-Level Systems: Developing reliable proof-of-concept exploits, analyzing novel exploitation vectors, and studying modern OS mitigation mechanisms across x86 and ARM architectures.
  • AI & Machine Learning for Cybersecurity: Applying representation learning, NLP on code, and behavioral analytics to automate silent security patch detection and software security verification.
  • Time-Series Modeling & Systems Telemetry: Deep sequence architectures (LSTM) and non-uniform temporal aggregations for continuous system telemetry and process modeling.

Selected Publications

PatchView: Multi-modality detection of security patches

Computers & Security, 2025
Nitzan Farhi, Noam Koenigstein, Yuval Shavitt

  • Highlights: 94.5% Accuracy · 95.1% F1-Score · 0.97 AUC. Introduces a multi-modal deep learning model combining source code representations, commit messages, and behavioral repository metadata to detect security patches.
  • [Paper / DOI]   [Code (GitHub)]   [Dataset (Kaggle)]

Detecting Security Patches via Behavioral Data in Code Repositories

arXiv / AAAI AICS, 2023
Nitzan Farhi, Noam Koenigstein, Yuval Shavitt

  • Highlights: 88.3% Accuracy · 89.8% F1-Score. Proposes a language-oblivious methodology that identifies silent security patches across repositories solely through developer behavioral metadata.
  • [Paper (arXiv)]   [Code (GitHub)]   [Dataset (Kaggle)]

Malboard: A novel user keystroke impersonation attack and trusted detection framework based on side-channel analysis

Computers & Security, 2019
Nitzan Farhi, Nir Nissim, Yuval Elovici

  • Highlights: Investigates physical weaponized USB keyboard implants that evade traditional behavioral biometric defenses, and presents a trusted detection framework using acoustic and keystroke side-channel telemetry.
  • [Paper / DOI]

See all articles on the Publications page or on Google Scholar.

Education

  • Ph.D. in Electrical Engineering — Tel Aviv University
  • M.Sc. in Cyber Security — Ben-Gurion University
  • B.Sc. in Software Engineering — Ben-Gurion University

Connect

For professional background and career details, visit my LinkedIn profile or get in touch directly via Email.