Playing Offense and Defense with Deepfakes

Presented by

Mike Price, CTO at ZeroFOX and Matt Price, Principal Research Engineer at ZeroFOX

About this talk

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.

Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (14)
Subscribers (1333)
ZeroFOX, the market leader in social media & digital protection, safeguards modern organizations from dynamic security, brand and physical risks across social, mobile, web and collaboration platforms. Using diverse data sources and artificial intelligence-based analysis, the ZeroFOX Platform identifies and remediates targeted phishing attacks, credential compromise, data exfiltration, brand hijacking, executive and location threats and more. The patented ZeroFOX SaaS technology processes and protects millions of posts, messages and accounts daily across the social and digital landscape, spanning LinkedIn, Facebook, Slack, Twitter, Instagram, Pastebin, YouTube, mobile app stores, the deep & dark web, domains and more.