Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection

• URL: http://arxiv.org/abs/2604.12941v1
• Date: Tue, 14 Apr 2026 16:35:04 GMT
• Title: Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection
• Abstract summary: Continual face forgery detection requires detectors to learn emerging forgery paradigms without forgetting previously seen manipulations.<n>Existing CFFD methods rely on replaying a small amount of past data to mitigate forgetting.<n>We argue that the core role of replay in CFFD is to reinstate the distributions of previous forgery tasks during subsequent training.
• Score: 23.384166700988658
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual face forgery detection (CFFD) requires detectors to learn emerging forgery paradigms without forgetting previously seen manipulations. Existing CFFD methods commonly rely on replaying a small amount of past data to mitigate forgetting. Such replay is typically implemented either by storing a few historical samples or by synthesizing pseudo-forgeries from detector-dependent perturbations. Under strict memory budgets, the former cannot adequately cover diverse forgery cues and may expose facial identities, while the latter remains strongly tied to past decision boundaries. We argue that the core role of replay in CFFD is to reinstate the distributions of previous forgery tasks during subsequent training. To this end, we directly condense the discrepancy between real and fake distributions and leverage real faces from the current stage to perform distribution-level replay. Specifically, we introduce Distribution-Discrepancy Condensation (DDC), which models the real-to-fake discrepancy via a surrogate factorization in characteristic-function space and condenses it into a tiny bank of distribution discrepancy maps. We further propose Manifold-Consistent Replay (MCR), which synthesizes replay samples through variance-preserving composition of these maps with current-stage real faces, yielding samples that reflect previous-task forgery cues while remaining compatible with current real-face statistics. Operating under an extremely small memory budget and without directly storing raw historical face images, our framework consistently outperforms prior CFFD baselines and significantly mitigates catastrophic forgetting. Replay-level privacy analysis further suggests reduced identity leakage risk relative to selection-based replay.

Related papers

• Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems [16.685352002333225]
  Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose likelihood component is generally intractable.<n>We show that a noise-conditioned path whose targets approach the clean posterior produces a continuous surrogate SDE.<n>Experiments on FFHQ and ImageNet with 100 score evaluations demonstrate competitive reconstruction fidelity for superresolution and deblurring.
  arXiv  Detail & Related papers  (2026-08-15T09:38:41Z)
• Sharp Convergence Rates for Masked Diffusion Models [53.117058231393834]
  We develop a total-variation based analysis for the Euler method that overcomes limitations.<n>Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees.<n>Overall, our analysis introduces a direct TV-based error decomposition along the CTMC trajectory and a decoupling-based path-wise analysis for FHS.
  arXiv  Detail & Related papers  (2026-02-26T00:47:51Z)
• When Generative Replay Meets Evolving Deepfakes: Domain-Aware Relative Weighting for Incremental Face Forgery Detection [20.277608307966382]
  Generative replay offers a potential solution by synthesizing past data, but its feasibility for forgery detection remains unclear.<n>We propose a novel Domain-Aware Relative Weighting (DARW) strategy to exploit generative replay effectively.<n>DARW directly supervises domain-safe samples while applying a Relative Separation Loss to balance supervision and potential confusion for domain-risky samples.
  arXiv  Detail & Related papers  (2025-11-23T13:09:02Z)
• Pr$^2$R: Information-Fused and Style-Aware Privacy-Preserving Replay for Lifelong Person Re-Identification [8.86871840837003]
  Lifelong person re-identification (LReID) aims to incrementally accumulate knowledge across a sequence of tasks under domain shifts.<n>Recent replay-based methods have demonstrated strong effectiveness in LReID by rehearsing past samples stored in an auxiliary memory.<n>We propose to fuse information from sequential data into the pixel space in the replay memory, enabling Privacy-Preserving Replay (Pr$2$R)
  arXiv  Detail & Related papers  (2025-08-03T05:00:19Z)
• Rectified Diffusion Guidance for Conditional Generation [94.83538269086613]
  We revisit the theory behind CFG and rigorously confirm that the improper combination coefficients (textiti.e.) brings about expectation shift the generative distribution.<n>We show that our approach enjoys a textbftextitform solution given the strength.<n> Empirical evidence on real-world data demonstrate the compatibility of our design with existing state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion [55.185588994883226]
  We introduce VQ-LCMD, a continuous-space latent diffusion framework within the embedding space that stabilizes training.<n>VQ-LCMD uses a novel training objective combining the joint embedding-diffusion variational lower bound with a consistency-matching (CM) loss.<n>Experiments show that the proposed VQ-LCMD yields superior results on FFHQ, LSUN Churches, and LSUN Bedrooms compared to discrete-state latent diffusion models.
  arXiv  Detail & Related papers  (2024-10-18T09:12:33Z)
• DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion [94.46904504076124]
  Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often struggle to generalize to unseen domains due to the diverse nature of facial manipulations. We introduce DiffusionFake, a novel framework that reverses the generative process of face forgeries to enhance the generalization of detection models.
  arXiv  Detail & Related papers  (2024-10-06T06:22:43Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay [16.269591842495892]
  We study a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains previous knowledge by concurrent replay of generated pseudo-data.
  arXiv  Detail & Related papers  (2024-04-16T15:39:11Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [93.90047628101155]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks.<n>To address this, some methods propose replaying data from previous tasks during new task learning.<n>However, it is not expected in practice due to memory constraints and data privacy issues.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Continual Face Forgery Detection via Historical Distribution Preserving [88.66313037412846]
  We focus on a novel and challenging problem: Continual Face Forgery Detection (CFFD) CFFD aims to efficiently learn from new forgery attacks without forgetting previous ones. Our experiments on the benchmarks show that our method outperforms the state-of-the-art competitors.
  arXiv  Detail & Related papers  (2023-08-11T16:37:31Z)
• 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)

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.