Tackling Deepfakes - Battling Ai-Generated Faces, Scams, Detection, And Security – Sankalp Kumar

In this episode of the Security Repo Podcast, Dwayne McDaniel and Sankalp Kumar dive into the world of deepfakes, how they are created using transformer models and GANs, and the real-world scams they enable. They discuss current detection techniques, including physiological analysis, iris scanning, and PKI-based authentication. Sankalp also shares actionable advice for security teams to adopt existing tools and prepare for the evolving deepfake threat landscape.

With over 7 years of experience working with industry giants like McAfee, Juniper, and Fraunhofer, Sankalp Kumar has consistently been at the forefront of security innovation. He has expertise in building software systems that do intrusion detection and was one of the lead engineers in building McAfee’s IPS. Today, Sankalp leads efforts for scaling, improving network software stacks, and securing software systems.

Further reading for the audience:

(1) News article for deep fake scams:

DOJ's probe into Doppelganger: https://www.justice.gov/archives/opa/pr/justice-department-disrupts-covert-russian-government-sponsored-foreign-malign-influence

Deepfake CFO scam: https://www.cnn.com/2024/02/04/asia/deepfake-cfo-scam-hong-kong-intl-hnk/index.html

(2) Some tools for further understanding the detection of deep fakes:

Darpa MediFor: https://www.darpa.mil/research/programs/media-forensics

Microsoft Video Authentication: https://blogs.microsoft.com/on-the-issues/2020/09/01/disinformation-deepfakes-newsguard-video-authenticator/