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

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.