ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors

TL;DR

ExposeAnyone introduces a self-supervised diffusion-based model that personalizes expression sequences from audio to detect unseen face forgeries with high robustness and improved accuracy over previous methods.

Contribution

The paper presents a novel self-supervised diffusion model for face forgery detection that personalizes to individuals and generalizes well to unseen manipulations.

Findings

Outperforms previous state-of-the-art by 4.22% in average AUC.

Capable of detecting Sora2-generated videos.

Highly robust to image corruptions like blur and compression.

Abstract

Detecting unknown deepfake manipulations remains one of the most challenging problems in face forgery detection. Current state-of-the-art approaches fail to generalize to unseen manipulations, as they primarily rely on supervised training with existing deepfakes or pseudo-fakes, which leads to overfitting to specific forgery patterns. In contrast, self-supervised methods offer greater potential for generalization, but existing work struggles to learn discriminative representations only from self-supervision. In this paper, we propose ExposeAnyone, a fully self-supervised approach based on a diffusion model that generates expression sequences from audio. The key idea is, once the model is personalized to specific subjects using reference sets, it can compute the identity distances between suspected videos and personalized subjects via diffusion reconstruction errors, enabling person-of-interest face forgery detection. Extensive experiments demonstrate that 1) our method outperforms the previous state-of-the-art method by 4.22 percentage points in the average AUC on DF-TIMIT, DFDCP, KoDF, and IDForge datasets, 2) our model is also capable of detecting Sora2-generated videos, where the previous approaches perform poorly, and 3) our method is highly robust to corruptions such as blur and compression, highlighting the applicability in real-world face forgery detection.