Toward Calibrated, Fair, and accurate Deepfake Detection

• URL: http://arxiv.org/abs/2606.09881v1
• Date: Wed, 03 Jun 2026 05:44:29 GMT
• Title: Toward Calibrated, Fair, and accurate Deepfake Detection
• Abstract summary: Deepfake detectors show large performance gaps across demographic groups.<n>Existing fairness approaches require demographic labels, retraining, or sacrifice accuracy.<n>We introduce Face-Fairness (FF), a plug-and-play framework for bias mitigation.
• Score: 5.183958775837362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacrifice accuracy. We introduce Face-Fairness (FF), a plug-and-play framework for bias mitigation. Our primary contribution, Face-Feature Tuning (FFT), is the first demographic label-free fairness method demonstrated for deepfake detection: a lightweight calibrator that performs a logit remapping conditioned on frozen face embeddings. We complement FFT with two variants: FF-Max, which maximizes worst-group accuracy when demographics are available, and FF-Discover, which does the same with embedding-discovered groups. Across in-domain and cross-dataset test settings, FF consistently reduces FPR/TPR gaps and improves minimum group accuracy while maintaining (often improving) overall accuracy. The approach is detector-agnostic, adds negligible runtime overhead, and requires no access to identity attributes.

Related papers

• FairReL: Deepfake Detection using Fairness-Aware Representation Learning [13.693865200913741]
  We propose a fairness-aware representation-learning framework that targets subgroup-sensitive components.<n>FairReL uses an SVD-decomposed foundation-model backbone to isolate the fine-tuning-induced residual representation.<n>Experiments on FF++, Celeb-DF, DFD and DFDC show that, against the state-of-the-art fairness-aware detector, FairReL improves unseen-dataset AUC by 3.9% while reducing subgroup FPR disparity by 10.2%.
  arXiv  Detail & Related papers  (2026-08-28T18:34:15Z)
• Estimating Fair Graphs from Graph-Stationary Data [58.94389691379349]
  We consider group and individual fairness for graphs corresponding to group- and node-level definitions.<n>To evaluate the fairness of a given graph, we provide multiple bias metrics, including novel measurements in the spectral domain.<n>One variant of FairSpecTemp exploits commutativity properties of graph stationarity while directly constraining bias.<n>The other implicitly encourages fair estimates by restricting bias in the graph spectrum and is thus more flexible.
  arXiv  Detail & Related papers  (2025-10-08T20:51:57Z)
• Fair-FLIP: Fair Deepfake Detection with Fairness-Oriented Final Layer Input Prioritising [1.3348326328808557]
  Deepfake detection methods often exhibit biases across demographic attributes such as ethnicity and gender.<n>We propose a novel post-processing approach, referred to as Fairness-Oriented Final Layer Input Prioritising (Fair-FLIP)<n>We show that Fair-FLIP can enhance fairness metrics by up to 30% while maintaining baseline accuracy, with only a negligible reduction of 0.25%.
  arXiv  Detail & Related papers  (2025-07-11T15:17:02Z)
• Fair Deepfake Detectors Can Generalize [51.21167546843708]
  We show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions.<n>Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals.<n>DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art
  arXiv  Detail & Related papers  (2025-07-03T14:10:02Z)
• Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations [63.52709761339949]
  We first contribute a dedicated dataset called the Fair Forgery Detection (FairFD) dataset, where we prove the racial bias of public state-of-the-art (SOTA) methods.<n>We design novel metrics including Approach Averaged Metric and Utility Regularized Metric, which can avoid deceptive results.<n>We also present an effective and robust post-processing technique, Bias Pruning with Fair Activations (BPFA), which improves fairness without requiring retraining or weight updates.
  arXiv  Detail & Related papers  (2024-07-19T14:53:18Z)
• Fairly Accurate: Fairness-aware Multi-group Target Detection in Online Discussion [8.812487330632282]
  We focus on the fairness implications of target-group detection in the context of toxicity detection.<n>Because toxicity is highly contextual, language that appears benign in general may be harmful when targeting specific demographic groups.<n>We show that our proposed approach to em fairness-aware multi target-group detection achieves competitive predictive performance, outperforming existing fairness-aware baselines.
  arXiv  Detail & Related papers  (2024-07-16T17:23:41Z)
• Minimax Optimal Fair Classification with Bounded Demographic Disparity [28.936244976415484]
  This paper explores the statistical foundations of fair binary classification with two protected groups. We show that using a finite sample incurs additional costs due to the need to estimate group-specific acceptance thresholds. We propose FairBayes-DDP+, a group-wise thresholding method with an offset that we show attains the minimax lower bound.
  arXiv  Detail & Related papers  (2024-03-27T02:59:04Z)
• Preserving Fairness Generalization in Deepfake Detection [14.485069525871504]
  Deepfake detection models can result in unfair performance disparities among demographic groups, such as race and gender. We propose the first method to address the fairness generalization problem in deepfake detection by simultaneously considering features, loss, and optimization aspects. Our method employs disentanglement learning to extract demographic and domain-agnostic features, fusing them to encourage fair learning across a flattened loss landscape.
  arXiv  Detail & Related papers  (2024-02-27T05:47:33Z)
• Fair-CDA: Continuous and Directional Augmentation for Group Fairness [48.84385689186208]
  We propose a fine-grained data augmentation strategy for imposing fairness constraints. We show that group fairness can be achieved by regularizing the models on transition paths of sensitive features between groups. Our proposed method does not assume any data generative model and ensures good generalization for both accuracy and fairness.
  arXiv  Detail & Related papers  (2023-04-01T11:23:00Z)
• Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach [72.19525160912943]
  We first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. We then analyze the sufficient conditions to guarantee fairness for the target dataset. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR)
  arXiv  Detail & Related papers  (2023-03-06T17:19:23Z)
• On Comparing Fair Classifiers under Data Bias [42.43344286660331]
  We study the effect of varying data biases on the accuracy and fairness of fair classifiers. Our experiments show how to integrate a measure of data bias risk in the existing fairness dashboards for real-world deployments.
  arXiv  Detail & Related papers  (2023-02-12T13:04:46Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.