Gumbel Rao Monte Carlo based Bi-Modal Neural Architecture Search for Audio-Visual Deepfake Detection

TL;DR

This paper introduces GRMC-BMNAS, a novel neural architecture search framework using Gumbel-Rao Monte Carlo sampling to optimize multimodal fusion for deepfake detection, achieving high accuracy with minimal parameters.

Contribution

It proposes a new architecture search method that refines Gumbel Softmax with Rao-Blackwellization, improving stability and performance in multimodal deepfake detection.

Findings

Achieved 95.4% AUC on FakeAVCeleb and SWAN-DF datasets.

Efficiently identifies crucial features from backbone networks.

Optimizes architecture for better generalization and classification performance.

Abstract

Deepfakes pose a critical threat to biometric authentication systems by generating highly realistic synthetic media. Existing multimodal deepfake detectors often struggle to adapt to diverse data and rely on simple fusion methods. To address these challenges, we propose Gumbel-Rao Monte Carlo Bi-modal Neural Architecture Search (GRMC-BMNAS), a novel architecture search framework that employs Gumbel-Rao Monte Carlo sampling to optimize multimodal fusion. It refines the Straight through Gumbel Softmax (STGS) method by reducing variance with Rao-Blackwellization, stabilizing network training. Using a two-level search approach, the framework optimizes the network architecture, parameters, and performance. Crucial features are efficiently identified from backbone networks, while within the cell structure, a weighted fusion operation integrates information from various sources. By varying parameters such as temperature and number of Monte carlo samples yields an architecture that maximizes classification performance and better generalisation capability. Experimental results on the FakeAVCeleb and SWAN-DF datasets demonstrate an impressive AUC percentage of 95.4\%, achieved with minimal model parameters.