Nil Ashkenazi

Nil Ashkenazi is a Security Researcher at CyberArk Labs focused on AI security and the risks that arise when traditional software integrates with Large Language Models (LLMs). His research has surfaced multiple vulnerabilities at this boundary, from insecure tool integrations to prompt-driven abuse. Nil has been involved in creating "FuzzyAI," an automated framework for generating and evaluating jailbreaks against top LLMs. He’s passionate about making AI adoption safer.