Suppressing Gradient Conflict for Generalizable Deepfake Detection

TL;DR

This paper introduces a novel framework called CS-DFD that suppresses gradient conflicts during training, significantly improving deepfake detection accuracy and generalization across different manipulation techniques.

Contribution

The paper proposes the Conflict-Suppressed Deepfake Detection (CS-DFD) framework with two modules, UVS and CGR, to explicitly mitigate gradient conflicts and enhance model robustness.

Findings

Achieves state-of-the-art results on multiple deepfake benchmarks.

Improves cross-domain generalization in deepfake detection.

Effectively reduces gradient conflicts during training.

Abstract

Robust deepfake detection models must be capable of generalizing to ever-evolving manipulation techniques beyond training data. A promising strategy is to augment the training data with online synthesized fake images containing broadly generalizable artifacts. However, in the context of deepfake detection, it is surprising that jointly training on both original and online synthesized forgeries may result in degraded performance. This contradicts the common belief that incorporating more source-domain data should enhance detection accuracy. Through empirical analysis, we trace this degradation to gradient conflicts during backpropagation which force a trade-off between source domain accuracy and target domain generalization. To overcome this issue, we propose a Conflict-Suppressed Deepfake Detection (CS-DFD) framework that explicitly mitigates the gradient conflict via two synergistic modules. First, an Update Vector Search (UVS) module searches for an alternative update vector near the initial gradient vector to reconcile the disparities of the original and online synthesized forgeries. By further transforming the search process into an extremum optimization problem, UVS yields the uniquely update vector, which maximizes the simultaneous loss reductions for each data type. Second, a Conflict Gradient Reduction (CGR) module enforces a low-conflict feature embedding space through a novel Conflict Descent Loss. This loss penalizes misaligned gradient directions and guides the learning of representations with aligned, non-conflicting gradients. The synergy of UVS and CGR alleviates gradient interference in both parameter optimization and representation learning. Experiments on multiple deepfake benchmarks demonstrate that CS-DFD achieves state-of-the-art performance in both in-domain detection accuracy and cross-domain generalization.