Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection
Abstract
The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing deep learning-based detection methods rely on computationally intensive and energy-demanding inference algorithms, limiting their scalability. Here, we present a hybrid digital-analog deepfake video detection framework that combines a lightweight digital front-end with a spatially multiplexed optical decoding back-end for massively parallel analog inference through a programmable spatial light modulator. By simultaneously processing 15 or more video streams within a single optical propagation pass, the system enables high-throughput and accurate video-level authenticity prediction at reduced computational cost compared with purely digital methods. We validated this hybrid deepfake video processor using different datasets spanning classical face-swapping, real-world deepfake recordings, and fully AI-generated videos. Using a spatially multiplexed experimental set-up operating in the visible spectrum, we achieved average deepfake detection accuracy, sensitivity and specificity of 97.79%, 99.86% and 95.72%, respectively, on the Celeb-DF video dataset with 15 videos tested in parallel in a single optical pass per inference. The multiplexed optical decoder also demonstrates resilience against various types of video degradation, noise, compression, experimental misalignments and black-box adversarial attacks. Our results show that integrating optical computation into AI inference enables simultaneous gains in throughput, energy efficiency, and adversarial robustness - three properties that are difficult to achieve together in purely digital systems.
Versions
Related
- This is SParTA: A modular, efficient and scalable transformer architecture for jet-tagging
- Scalable Megapixel resolution Solid-State LiDAR architecture by Dual-MEMS coarse-fine Diffractive Beam Steering with Crosstalk Mitigation
- Spin-multiplexed terahertz image edge detection based on extrinsic chirality in all-dielectric metasurface
- A Scalable Two-Stage Back-End Architecture for 400GbE Data Acquisition Systems
- PolyUAnalog: A Modular and Scalable Open-Source Architecture for Polyphonic Analog Synthesis
BibTeX
@misc{kashani2026scalable,
title = {{Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection}},
author = {Parnian Ghapandar Kashani and Shiqi Chen and Aydogan Ozcan},
howpublished = {arXiv},
year = {2026},
month = may,
doi = {10.48550/arxiv.2605.19360},
eprint = {2605.19360},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.19360},
}
RIS
TY - UNPB
TI - Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection
AU - Parnian Ghapandar Kashani
AU - Shiqi Chen
AU - Aydogan Ozcan
PY - 2026
DA - 2026/05/19
PB - arXiv
DO - 10.48550/arxiv.2605.19360
UR - https://arxiv.org/abs/2605.19360
AB - The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing deep learning-based detection methods rely on computationally intensive and energy-demanding inference algorithms, limiting their scalability. Here, we present a hybrid digital-analog deepfake video detection framework that combines a lightweight digital front-end with a spatially multiplexed optical decoding back-end for massively parallel analog inference through a programmable spatial light modulator. By simultaneously processing 15 or more video streams within a single optical propagation pass, the system enables high-throughput and accurate video-level authenticity prediction at reduced computational cost compared with purely digital methods. We validated this hybrid deepfake video processor using different datasets spanning classical face-swapping, real-world deepfake recordings, and fully AI-generated videos. Using a spatially multiplexed experimental set-up operating in the visible spectrum, we achieved average deepfake detection accuracy, sensitivity and specificity of 97.79%, 99.86% and 95.72%, respectively, on the Celeb-DF video dataset with 15 videos tested in parallel in a single optical pass per inference. The multiplexed optical decoder also demonstrates resilience against various types of video degradation, noise, compression, experimental misalignments and black-box adversarial attacks. Our results show that integrating optical computation into AI inference enables simultaneous gains in throughput, energy efficiency, and adversarial robustness - three properties that are difficult to achieve together in purely digital systems.
ER -