Deepfake Sentry: Harnessing Ensemble Intelligence for Resilient Detection and Generalisation

TL;DR

This paper introduces an ensemble autoencoder-based data augmentation method to improve deepfake detection's robustness and generalization against various perturbations, adversarial attacks, and evolving generation techniques.

Contribution

It proposes a novel ensemble autoencoder approach that introduces artificial fingerprints into training data, enhancing deepfake detection resilience and generalization.

Findings

Improved robustness against noise, blurring, and affine transforms.

Enhanced resistance to JPEG compression and adversarial attacks.

Better generalization across different deepfake datasets.

Abstract

Recent advancements in Generative Adversarial Networks (GANs) have enabled photorealistic image generation with high quality. However, the malicious use of such generated media has raised concerns regarding visual misinformation. Although deepfake detection research has demonstrated high accuracy, it is vulnerable to advances in generation techniques and adversarial iterations on detection countermeasures. To address this, we propose a proactive and sustainable deepfake training augmentation solution that introduces artificial fingerprints into models. We achieve this by employing an ensemble learning approach that incorporates a pool of autoencoders that mimic the effect of the artefacts introduced by the deepfake generator models. Experiments on three datasets reveal that our proposed ensemble autoencoder-based data augmentation learning approach offers improvements in terms of generalisation, resistance against basic data perturbations such as noise, blurring, sharpness enhancement, and affine transforms, resilience to commonly used lossy compression algorithms such as JPEG, and enhanced resistance against adversarial attacks.