FairReL: Deepfake Detection using Fairness-Aware Representation Learning

• URL: http://arxiv.org/abs/2608.28777v1
• Date: Fri, 28 Aug 2026 18:34:15 GMT
• Title: FairReL: Deepfake Detection using Fairness-Aware Representation Learning
• Abstract summary: 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%.
• Score: 13.693865200913741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although recent deepfake detectors achieve high overall accuracy, their errors remain unevenly distributed across demographic subgroups, with real faces from certain groups more often misclassified as fake. Existing fairness-aware detectors typically regularise the entire feature representation, without identifying or controlling the specific components that drive unfair predictions. Such coarse intervention can over-suppress useful forgery cues while leaving demographic structure in component-specific subspaces. To address this, we identify two subgroup-sensitive components: multi-scale spatial features, which encode local facial and forgery patterns, and fine-tuning-induced residual features, which adapt the backbone to the unfair training distribution. We propose FairReL, a fairness-aware representation-learning framework that targets both components with dedicated demographic supervision. FairReL uses an SVD-decomposed foundation-model backbone to isolate the fine-tuning-induced residual representation, and introduces two complementary losses. Group-Conditional Wavelet Decorrelation (GCWD) suppresses subgroup-imbalanced structure across spatial wavelet sub-bands, while Subspace-Localised Mean Alignment (SLMA) aligns subgroup means within each real/fake class in the residual representation. 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%. Code is available at https://github.com/xiaoman89/FairReL .

Related papers

• Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification [2.9276026564633617]
  Local Reference Geometry (LRG) is a lightweight feature augmentation module for time series classification.<n>LRG measures local exposure and class-mixture risk, then augments each fixed feature with a standardized signed displacement from nearby training geometry.<n>On controlled UCR/Bake Off Redux imbalance benchmarks, paired raw--LRG comparisons show gains for learned, pretrained, and fixed representations.
  arXiv  Detail & Related papers  (2026-08-31T13:50:40Z)
• Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization [2.6245086561385276]
  We propose an end-to-end Mixture-of-Experts (MoE) framework that corrects subgroup imbalance.<n>We apply subgroup reweighting to correct data imbalance, and introduce gate entropy regularization to prevent routing from collapsing onto subgroup attributes.<n> Experimental results demonstrate that the proposed approach improves fairness while maintaining competitive predictive performance.
  arXiv  Detail & Related papers  (2026-08-24T05:34:25Z)
• Toward Calibrated, Fair, and accurate Deepfake Detection [5.183958775837362]
  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.
  arXiv  Detail & Related papers  (2026-06-03T05:44:29Z)
• Unsupervised Domain Shift Detection with Interpretable Subspace Attribution [48.553902624178995]
  Domain shifts are subtle differences in the probability distributions of datasets.<n>We identify these shifts using an algorithm designed to detect localised density anomalies in high-dimensional feature spaces.<n>We trace the domain shift to a small set of features, making the shift interpretable.
  arXiv  Detail & Related papers  (2026-05-15T12:58:00Z)
• REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature [16.040317742756034]
  We propose REMISVFU, a plug-and-play representation misdirection framework that enables fast, client-level unlearning in splitVFL systems.<n>We show that REMISVFU suppresses back-door attack success to the natural class-prior level and sacrifices only about 2.5% points of clean accuracy.
  arXiv  Detail & Related papers  (2025-12-11T07:05:36Z)
• Real-Aware Residual Model Merging for Deepfake Detection [29.454462278073063]
  Deepfake generators evolve quickly, making exhaustive data collection and repeated retraining impractical.<n>We propose Real-aware Residual Model Merging (R$2$M), a training-free parameter-space merging framework.<n>R$2$M estimates a shared Real component via a low-rank factorization of task vectors, decomposes each specialist into a Real-aligned part and a Fake residual, denoises residuals with layerwise rank truncation, and aggregates them with per-task norm matching.
  arXiv  Detail & Related papers  (2025-09-29T07:10:03Z)
• 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)
• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness [61.45587642780908]
  We propose a three-step approach for parameter-efficient fine-tuning of image-text foundation models.<n>Our method improves its two key components: minority samples identification and the robust training algorithm.<n>Our theoretical analysis shows that our PPA enhances minority group identification and is Bayes optimal for minimizing the balanced group error.
  arXiv  Detail & Related papers  (2025-03-12T15:46:12Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• Global Distance-distributions Separation for Unsupervised Person Re-identification [93.39253443415392]
  Existing unsupervised ReID approaches often fail in correctly identifying the positive samples and negative samples through the distance-based matching/ranking. We introduce a global distance-distributions separation constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view. We show that our method leads to significant improvement over the baselines and achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-06-01T07:05:39Z)

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.