Suppressing Gradient Conflict for Generalizable Deepfake Detection

• URL: http://arxiv.org/abs/2507.21530v1
• Date: Tue, 29 Jul 2025 06:48:22 GMT
• Title: Suppressing Gradient Conflict for Generalizable Deepfake Detection
• Authors: Ming-Hui Liu, Harry Cheng, Xin Luo, Xin-Shun Xu,
• Abstract summary: We propose a Conflict-Suppressed Deepfake Detection (CS-DFD) framework that explicitly mitigates the gradient conflict via two synergistic modules.<n> 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.
• Score: 13.33948815738503
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TIP: Resisting Gradient Inversion via Targeted Interpretable Perturbation in Federated Learning [8.156452885913108]
  Federated Learning (FL) facilitates collaborative model training while preserving data locality.<n>The exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs)<n>We propose Targeted Interpretable Perturbation (TIP), a novel defense framework that integrates model interpretability with frequency domain analysis.
  arXiv  Detail & Related papers  (2026-02-12T06:32:49Z)
• ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning [85.20505958752928]
  Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment.<n>RFT often introduce visual hallucinations like over-optimized details and semantic misalignment.<n>This work preliminarily explores why visual hallucinations arise and how to reduce them.
  arXiv  Detail & Related papers  (2026-02-03T11:49:46Z)
• Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection [60.515439134387755]
  We propose a dual-path data-augmented (DPDA) training framework with gradient alignment for speech deepfake detection (SDD)<n>In our framework, each training utterance is processed through two input paths: one using the original speech and the other with its augmented version.<n>Our method achieves up to an 18.69% relative reduction in Equal Error Rate on the In-the-Wild dataset compared to the baseline.
  arXiv  Detail & Related papers  (2025-09-25T02:31:54Z)
• RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment [13.327130030147565]
  We propose a novel learning objective that aligns generalization gradient updates with ERM gradient updates.<n>The key innovation is the application of perturbations to model parameters, aligning the ascending points across domains.<n> Experimental results on multiple challenging deepfake detection datasets demonstrate that our gradient alignment strategy outperforms state-of-the-art domain generalization techniques.
  arXiv  Detail & Related papers  (2025-05-27T03:02:21Z)
• A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection [9.335304254034401]
  We introduce a lightweight, plug-in detection framework that leverages internal layer-wise inconsistencies within the target model itself.<n>Our method achieves state-of-the-art detection performance with negligible computational overhead and no compromise to clean accuracy.
  arXiv  Detail & Related papers  (2025-05-19T00:48:53Z)
• Robust AI-Generated Face Detection with Imbalanced Data [10.360215701635674]
  Current deepfake detection techniques have evolved from CNN-based methods focused on local artifacts to more advanced approaches using vision transformers and multimodal models like CLIP.<n>Despite recent progress, state-of-the-art deepfake detectors still face major challenges in handling distribution shifts from emerging generative models.<n>We propose a framework that combines dynamic loss reweighting and ranking-based optimization, which achieves superior generalization and performance under imbalanced dataset conditions.
  arXiv  Detail & Related papers  (2025-05-04T17:02:10Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches [4.577842191730992]
  We study ways toward robust OoD generalization for deep learning. We first propose a novel and effective approach to disentangle the spurious correlation between features that are not essential for recognition. We then study the problem of strengthening neural architecture search in OoD scenarios.
  arXiv  Detail & Related papers  (2024-10-25T20:50:32Z)
• Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection [41.35861722481721]
  Deepfake threats to society and cybersecurity have provoked significant public apprehension. This paper introduces an elegantly simple yet effective strategy named Thumbnail Layout (TALL) TALL transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies.
  arXiv  Detail & Related papers  (2024-03-15T12:48:44Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Boosting Gradient for White-Box Adversarial Attacks [60.422511092730026]
  We propose a universal adversarial example generation method, called ADV-ReLU, to enhance the performance of gradient based white-box attack algorithms. Our approach calculates the gradient of the loss function versus network input, maps the values to scores, and selects a part of them to update the misleading gradients.
  arXiv  Detail & Related papers  (2020-10-21T02:13:26Z)
• Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification [93.2334223970488]
  We propose two regularizers to prevent hypersphere collapse in deep SVDD. The first regularizer is based on injecting random noise via the standard cross-entropy loss. The second regularizer penalizes the minibatch variance when it becomes too small.
  arXiv  Detail & Related papers  (2020-01-24T03:44:47Z)

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.