Author:
Zvika Babo
Zvika Babo is a Security Researcher at Radware, specializing in LLM and agentic security. His work focuses on identifying and analyzing vulnerabilities in AI-powered agents, with an emphasis on prompt injection attacks, tool misuse, and emerging risks in autonomous systems. In addition to offensive research, Zvika designs and develops detection mechanisms and algorithms to mitigate prompt injection attacks and strengthen the security of LLM-based agents in real-world environments.