Virginia Tech® home

Piloting a Human-AI Cooperative System to Detect Automated Deepfake Deception

Dr. Giuseppe Ateniese
Dr. Giuseppe Ateniese

Dr. Giuseppe Ateniese

KEY INTERESTS

Cloud security; Cybersecurity; Applied cryptography

AFFILIATIONS/APPOINTMENTS

Professor and Eminent Scholar, Department of Cyber Security Engineering and Department of Computer Science, George Mason University

Faculty Fellow, Commonwealth Cyber Initiative

ACADEMIC DEGREES

Laurea (MSc), Computer Science, University of Salerno

PhD, Computer Science, University of Genoa

PILOTING A HUMAN-AI COOPERATIVE SYSTEM TO DETECT AUTOMATED DEEPFAKE DECEPTION

In June 2022, the mayors of several European cities were deceived into holding video conference calls with a deepfake version of Mayor Vitali Klitschko, their counterpart in Kyiv, Ukraine. Although this imposter was eventually discovered, this attempt reveals the potential national security risks posed by cyber threat actors using deepfake technology to facilitate their attacks. In this case, there appeared to be a human controlling the deepfake, but it is now (or soon will be) possible for automated ‘bots’ to control such deepfakes, allowing threat actors to launch targeted attacks at scale. Synthetic media (the automated generation of text, audio, and video) presents a game-changing capability to cyber threat actors and represents a clear and present danger to national security. This project seeks to begin development of a new method to detect automation-enabled social engineering attacks, in near real-time, using a hybrid human-AI system.