esc

Type at least two characters to start searching.

↑↓ select↵ openesc close

Share

Export Citation

APA
MLA
Chicago
Harvard
Vancouver
BIBTEX
RIS
Universitas Hasanuddin
Research output:Contribution to journal›Article›peer-review

DS-Xception: Dual-Stream Noise Residual Architecture with Few-Shot Domain Anchor for Generalizable Diffusion-Based Deepfake Video Detection

Slat C.C.

2026 IEEE International Conference on Artificial Intelligence and Mechatronics Systems Aims 2026

Published: 2026

Abstract

The rapid shift from Generative Adversarial Networks (GANs) to diffusion models has rendered conventional deepfake detectors ineffective, as GAN-optimized architectures suffer catastrophic cross-domain performance drops. We reveal a critical motion-field divergence where GAN content exhibits erratic temporal fields while diffusion pipelines produce excessively smooth trajectories, creating a motion smoothness trap that yields an average cross-domain predicted fake probability of only 7.43%. To address this, we propose DS-Xception, a dual-stream architecture fusing a spatial stream with a Photo Response Non-Uniformity (PRNU) noise residual stream, augmented by a Few-Shot Domain Anchor strategy injecting only 50 diffusion samples (0.5% of training data) to calibrate cross-paradigm decision boundaries. DS-Xception achieves a cross-domain AUC of 0.9257 and recall of 86.06%, up from a baseline of 0.6234, while preserving an intra-domain AUC of 0.9989.

Other files and links

Fingerprint

Computer scienceSciences
ResidualSciences
Domain (mathematical analysis)Sciences
Noise (video)Sciences
Artificial intelligenceSciences
Computer visionSciences
Pattern recognition (psychology)Sciences
ArchitectureSciences
AlgorithmSciences
Background noiseSciences
Key (lock)Sciences
Object detectionSciences
Machine learningSciences
Signal processingSciences
Measure (data warehouse)Sciences
Noise reductionSciences