Document Type
Conference Material
Abstract/Description
Deepfakes have rapidly emerged as one of the most pressing threats to information integrity and security, precisely because they are designed to exploit human trust in visual and auditory perception. Yet, little is known about whether humans and their underlying (sub)conscious neuro-physiological processes can reliably distinguish deepfake vs. real videos. We introduce DECEIVE (Deepfake Exploitation of Cognitive Engagement and Implicit Visual Evaluation), a framework that models how deepfake videos are validated as adversarial payloads through behavioral and neuro-physiological screening of viewers, and how an attack is iteratively refined by selecting the payloads that evade detection. The framework is dataset agnostic and applies to any synthetic or real media. Such a framework is inherently dual-use: an adversary with equivalent measurements could iterate on candidate manipulations and keep those that evade human detection, which is precisely why the evaluation should be conducted openly and defensively. Measuring which deepfakes already defeat human perception establishes a realistic bound on attacker capability, against which detection tooling, provenance and watermarking mechanisms, and user-facing protections can be assessed. As an instantiation, we conducted an EEG and eye-tracking study in which participants viewed real, deepfake, and look-alike videos drawn from Celeb-DF and a curated celebrity set, while their behavioral judgments and implicit responses were recorded. Contrary to expectations of subconscious differentiation suggested by prior work on paintings and phishing websites, no statistically significant neuro-physiological differences emerged between real and deepfake videos, although clear distinctions were observed for look-alike videos. Behaviorally, participants accepted 26.68% of manipulated clips as authentic, rising to 31.94% for familiar identities, confirming the studied deepfakes as effective adversarial payloads within the DECEIVE framework.
Department
Computer Science and Information Systems
DOI
10.48550/arXiv.2609.32769
Date
9-26-2026
Conference Title
29th Information Security Conference
Conference Location
Rennes, France
Citation Information
Arisoy, Cagri; Huq, Md Imanul; Hays, Amy; and Saxena, Nitesh, "You Can't Spot a Deepfake — And Neither Can Your Brain Nor Eyes: A Neurophysiological Framework for Deepfake Exploitation of Cognitive Engagement and Implicit Visual Evaluation" (2026). Faculty Publications. 267.
https://lair.etamu.edu/cose-faculty-publications/267
