Shir Rozenfeld
AI Safety and Security Researcher.
AI Researcher @ Microsoft Security · PhD Candidate @ BGU
About
I'm an AI Researcher at the Cyber Security GenAI Lab in the Microsoft Security CTO Office, and a PhD candidate at Ben-Gurion University, where I do Technical AI Safety research in the Offensive AI Research Lab. Earlier, I led the development of GAVEL, an open-source framework for detecting misaligned behaviors and intentions in LLMs through activation analysis (ICLR 2026; Black Hat USA 2026 Briefing). Before that, I led a data analysis team on national security missions.
Research interests
LLM safety · activation-analysis · mechanistic interpretability · AI agents · model behavior & intention detection · offensive AI
Education
- Ph.D. in AGI Safety, Ben-Gurion University
- M.Sc. in Data Science, Ben-Gurion University
- B.Sc. in Software and Information Systems Engineering, Ben-Gurion University
News
🎉 Our research was featured in WIRED!
Andy Greenberg covered our research on AI-powered romance-baiting scams in “AI Scammers Are Better at Building Trust Than Humans” .
🎤 Giving a talk at Black Hat USA 2026 Briefings
Presenting an extension of our work at one of the world's top cybersecurity conferences, August 5–6 in Las Vegas. “Rules for Neural Traffic: A New Defensive Layer for LLMs” .
🎤 Gave a talk at Heron Lightning Talks, TLV
A lightning talk on recent advancements in AI Safety for the AI Security community.
🌍 EA Global: London 2026
Attended EAG London to connect with the AI safety community.
🎉 Paper accepted at USENIX Security 2026
Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams — arXiv
Research
LLM safety & activation monitoring
Real-time detection of unsafe or misaligned behavior by monitoring a model's internal activations — the line of work behind GAVEL.
Mechanistic Interpretability
Understanding the internal computations of language models, from individual features up to circuits.
Contact
I'm glad to talk about LLM safety, interpretability, and offensive AI. The best ways to reach me are email and LinkedIn.