Ben Nassi

Dr. Ben Nassi is a cybersecurity researcher and white-hat hacker specializing in AI security, cryptanalysis, and cyber-physical systems. Nassi holds a Bachelor of Science in computer science, a Master of Science in software engineering, and a doctorate in security and privacy in the IoT era from Ben-Gurion University. He began his career at Deutsche Telekom Innovation Labs as a researcher and software developer, later completing a postdoctoral fellowship at Cornell Tech as a Jacobs Urban Tech Hub Fellow before joining the School of Electrical Engineering at Tel Aviv University as a faculty member.

Nassi is recognized for his work in video-based cryptanalysis. He developed a method to recover secret keys from non-compromised devices by analyzing video footage of a device's power LED. This research demonstrated that cryptographic computations performed by a device's CPU alter its power consumption, affecting the brightness of the power LED—changes detectable by exploiting a video camera's rolling shutter. His team demonstrated the recovery of a 256-bit ECDSA key from a smartcard using video footage from a hijacked Internet-connected security camera located 16 meters away, and a 378-bit SIKE key from a Samsung Galaxy S8 using footage from a connected USB speaker via an iPhone. This study received the Pwnie Award for Best Crypto Attack.

Nassi's research extends to secret key recovery and audible speech recovery from a device's status LED. He gained international attention after remotely triggering Tesla's autopilot to stop the car in response to a compromised McDonald's advertisement presented on an Internet-connected digital billboard. Nassi also discovered a method to detect targeted drone activity in which a drone is illicitly filming a victim, research with implications for personal privacy and unmanned aerial vehicle security. He co-authored the paper introducing "Morris II," the first worm designed to target generative AI ecosystems through adversarial self-replicating prompts. The findings demonstrated how Morris II can exploit a generative AI email assistant, siphoning data from emails and sending spam, even bypassing some security measures in popular AI systems such as ChatGPT and Gemini.

Nassi is a frequent speaker at Black Hat, RSAC, and DEF CON events, and has served as a member of the Black Hat Review Board. He has received the Urban Tech Hub Fellowship, the Viterbi Fellowship for Nurturing Future Faculty Members, and the BGU Dean Award for Excellence in PhD. As a speaker, Nassi addresses security and privacy in AI-powered cyber-physical systems and explains advancements in cybersecurity. His work has been featured in Wired, Forbes, Ars Technica, The Wall Street Journal, MIT Technology Review, and Business Insider. Nassi is regarded as an authoritative voice in cybersecurity research, AI security, and cryptanalysis.