This presentation seeks to demonstrate how deepfaking can be leveraged for offensive and defensive purposes. Specifically, deepfake internals are presented including a fine grained, step-by-step breakdown of creation, including the details of all deep learning models used in the process. A test deepfake video is created. A malicious deepfake video is then created, in which an international politician is impersonated. This video is then temporarily circulated in the wild, as a means for measuring impact. The offense section of the presentation is followed by a defense section. This section provides an overview of contemporary techniques for detecting deepfake videos. A novel approach to detecting deepfake videos is then introduced. Finally, a tool for offensive and defensive research, known as deepstar, is announced and released at the time of the presentation.
Michael Price is currently Chief Technology Officer at the social media & digital protection startup ZeroFOX. He wrote his first line of BASIC on his mom's Commodore64 in the 80s and became involved with information security in the early 90s. He entered the information security field as a NASA contractor in 1999. He has otherwise worked professionally in the information security field for over 20 years. He has held major roles at several successful startups including Foundstone (acquired by McAfee), Appthority (acquired by Symantec), Vulnr (acquired by ZeroFOX) and ZeroFOX. Michael holds a Bachelor of Science in Security and Risk Analysis from The Pennsylvania State University, and is additionally a published author, a frequent speaker as well as co-founder of the first and only technical security conference in Chile - the 8.8 Computer Security Conference.
Matt Price is a Principal Research Engineer at ZeroFOX where he leads the company's AI and ML initiatives. He has over 5 years of experience in the information security field and over 10 years of experience in the information technology industry. He primarily focuses on applied AI to solve complex cyber security problems. Previously, Matt worked at FireEye and was the lead ML engineer on the static binary analysis model known as MalwareGuard.