Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies

TL;DR

This paper introduces an unsupervised deepfake detection method that identifies intra- and cross-modal inconsistencies in videos, effectively detecting deepfakes without needing labeled data or prior deepfake examples.

Contribution

It presents a novel unsupervised approach based on inconsistency detection, which is scalable, generalizable, reliable, and explainable, outperforming existing methods on challenging datasets.

Findings

Outperforms state-of-the-art unsupervised methods on FakeAVCeleb dataset

Does not require real samples for each identity during inference

Can pinpoint exact locations of modality inconsistencies

Abstract

Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting deepfakes, at scale, remains a very challenging task that often requires labeled training data from existing deepfake generation methods. Further, even the most accurate supervised deepfake detection methods do not generalize to deepfakes generated using new generation methods. In this paper, we propose a novel unsupervised method for detecting deepfake videos by directly identifying intra-modal and cross-modal inconsistency between video segments. The fundamental hypothesis behind the proposed detection method is that motion or identity inconsistencies are inevitable in deepfake videos. We will mathematically and empirically support this hypothesis, and then proceed to constructing our method grounded in our theoretical analysis. Our proposed method outperforms prior state-of-the-art unsupervised deepfake detection methods on the challenging FakeAVCeleb dataset, and also has several additional advantages: it is scalable because it does not require pristine (real) samples for each identity during inference and therefore can apply to arbitrarily many identities, generalizable because it is trained only on real videos and therefore does not rely on a particular deepfake method, reliable because it does not rely on any likelihood estimation in high dimensions, and explainable because it can pinpoint the exact location of modality inconsistencies which are then verifiable by a human expert.