With nearly 20 years of experience in the cyber-security industry, Guy held various positions in both corporates and startups.
His current focus is on Security for Machine Learning, System Architecture, and Cryptography, where he provides consulting services in these areas. He is well versed in the Security of machine learning systems, ever since publishing his first paper on using Neural Networks to detect genetic illness.
Most recently, he led Intel’s Predictive Threat Analysis group who focused on the security of machine learning systems and trusted execution environments. At Intel, he defined the global AI security strategy and roadmap. He spoke at dozens of events on the research he and the group have done on Security for AI systems and published several whitepapers on the subject.
Guy is the BSidesTLV chairman and CTF lead, a Public speaker in well known global security events (SAS, t2, 44CON, BSidesLV, and several DefCon villages to name a few), and the recipient of the Cisco “black belt” security ninja honor – Cisco’s highest cybersecurity advocate rank.
He started as a software developer for several security startups and later spent eight years in the IDF. After completing his degrees in Electrical Engineering and Applied Mathematics, he focused on security research, in real-world applications.
Needing a change, he joined a startup as a CTO. There, he led the team to a successful product, viable architecture, and roadmap.
|Stealth mode Startup||CTO and Co-Founder||2019-Now|
|BSidesTLV Chairman, CTF Lead||2017-Now|
|Security Research Manager||2017-2019|
|Cryptography, Supply Chain Security and Countermeasures Group Manager||2010-2015|
|B.Sc. in Electrical Engineering (cum laude) and B.Sc. in Applied Mathematics||2006-2010|
|Executive Officer, Chief Technician||1998-2005|
PROTECTION FOR INFERENCE ENGINE AGAINST MODEL RETRIEVAL ATTACK (July, 2018)
An embodiment of a semiconductor package apparatus may include technology to perform run-time analysis of inputs and outputs of a machine learning model of an inference engine, detect an activity indicative of an attempt to retrieve the machine learning model based on the run-time analysis, and perform one or more preventive actions upon detection of the activity indicative of the attempted model retrieval. Other embodiments are disclosed and claimed.