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

2026-09-26

AI Summary

This study addresses the security threat that deepfake videos can reliably evade human perception and underlying neural detection mechanisms. We propose DECEIVE, a framework that models how deepfakes circumvent cognitive detection by integrating electroencephalography (EEG) and eye-tracking for multimodal neurophysiological measurement. It establishes a dataset-agnostic, dual-purpose evaluation system to quantify perceptual blind spots and optimize adversarial payloads. Experimental results demonstrate that real and fake videos elicit no significant neural discrepancies, with 26.68% of forged videos misclassified as authentic, thereby validating their effectiveness as adversarial payloads. This work establishes a benchmark for defensive evaluation and delineates realistic boundaries for adversarial security analysis in deepfake detection.

Abstract

Deepfakes have rapidly emerged as a pressing threat to information integrity and security because they 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 from 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 attacks can be refined by selecting payloads that evade detection. The framework is dataset agnostic and applies to synthetic or real media. It is inherently dual-use: an adversary with equivalent measurements could iterate on candidate manipulations and retain those that evade human detection. This motivates open, defensive evaluation. Measuring which deepfakes 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 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 DECEIVE.

Problem

• Deepfake
• neurophysiological processes
• cognitive engagement
• visual evaluation
• human perception

Innovation

• Deepfake
• Neurophysiological Framework
• EEG
• Eye-tracking
• Adversarial Payloads