Rethinking Individual Fairness in Deepfake Detection

TL;DR

This paper reveals that traditional individual fairness principles fail in deepfake detection and introduces a new framework that improves fairness without sacrificing detection accuracy, validated by extensive experiments.

Contribution

It identifies the failure of individual fairness in deepfake detection and proposes the first generalizable framework to enhance fairness and generalization.

Findings

Significant improvement in individual fairness metrics

Maintains robust deepfake detection performance

Outperforms state-of-the-art methods on leading datasets

Abstract

Generative AI models have substantially improved the realism of synthetic media, yet their misuse through sophisticated DeepFakes poses significant risks. Despite recent advances in deepfake detection, fairness remains inadequately addressed, enabling deepfake markers to exploit biases against specific populations. While previous studies have emphasized group-level fairness, individual fairness (i.e., ensuring similar predictions for similar individuals) remains largely unexplored. In this work, we identify for the first time that the original principle of individual fairness fundamentally fails in the context of deepfake detection, revealing a critical gap previously unexplored in the literature. To mitigate it, we propose the first generalizable framework that can be integrated into existing deepfake detectors to enhance individual fairness and generalization. Extensive experiments conducted on leading deepfake datasets demonstrate that our approach significantly improves individual fairness while maintaining robust detection performance, outperforming state-of-the-art methods. The code is available at https://github.com/Purdue-M2/Individual-Fairness-Deepfake-Detection.