Preserving Knowledge across Space and Time for Continual Video Deepfake Detection

• URL: http://arxiv.org/abs/2609.03446v1
• Date: Thu, 03 Sep 2026 07:02:51 GMT
• Title: Preserving Knowledge across Space and Time for Continual Video Deepfake Detection
• Abstract summary: Deepfake videos leave distinct evidence along both spatial and temporal axes.<n>We introduce a continual deepfake video detection framework, Modality-Specific Frequency Distillation (MSFD)<n>MSFD explicitly decomposes video features into spatial, temporal, andtemporal modalities.
• Score: 14.990460352014827
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The continuous emergence of high-quality video deepfakes requires detectors that continually adapt to new forgery patterns, yet existing approaches, which are designed for deepfake images, fail to capture video-specific cues. Unlike deepfake images that contain only spatial artifacts, deepfake videos leave distinct evidence along both spatial and temporal axes, necessitating the separate preservation of each modality during sequential model updates. To overcome this limitation, we introduce a continual deepfake video detection framework, Modality-Specific Frequency Distillation (MSFD), that explicitly decomposes video features into spatial, temporal, and spatiotemporal modalities in the frequency domain. This decomposition enables independent preservation of each modality, as different deepfake video types exhibit varying reliance on spatial and temporal cues across tasks. Furthermore, MSFD adopts a cross-modality decorrelation loss that encourages spatiotemporal representations to remain orthogonal to single-modality cues. Extensive experiments show that our framework achieves stronger adaptation and preserves performance more effectively than state-of-the-art methods across diverse continual deepfake video scenarios.

Related papers

• UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models [54.564740558030245]
  We present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism.<n>We also introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting.
  arXiv  Detail & Related papers  (2026-02-26T12:54:46Z)
• DiTVR: Zero-Shot Diffusion Transformer for Video Restoration [48.97196894658511]
  DiTVR is a zero shot video restoration framework that couples a diffusion transformer with trajectory aware attention and a flow consistent sampler.<n>Our attention mechanism aligns tokens along optical flow trajectories, with particular emphasis on vital layers that exhibit the highest sensitivity to temporal dynamics.<n>The flow guided sampler injects data consistency only into low-frequency bands, preserving high frequency priors while accelerating cache.
  arXiv  Detail & Related papers  (2025-08-11T09:54:45Z)
• Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency [1.7061868168035932]
  We propose a detection framework that leverages spatial-temporal consistency by combining RGB appearance features with optical flow residuals.<n>By integrating these complementary features, the proposed method effectively detects a wide range of forged videos.
  arXiv  Detail & Related papers  (2025-08-01T07:51:35Z)
• NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors [6.7253553166914255]
  We present NormalCrafter to leverage the inherent temporal priors of video diffusion models.<n>To secure high-fidelity normal estimation across sequences, we propose Semantic Feature Regularization.<n>We also introduce a two-stage training protocol to preserve spatial accuracy while maintaining long temporal context.
  arXiv  Detail & Related papers  (2025-04-15T17:39:07Z)
• Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts [57.01985221057047]
  This paper introduces a novel method that learnstemporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs) Our method achieves state-of-theart performance on three public benchmarks for the WSVADL task.
  arXiv  Detail & Related papers  (2024-08-12T03:31:29Z)
• Unearthing Common Inconsistency for Generalisable Deepfake Detection [8.327980745153216]
  Video-level one shows its potential to have both generalization across multiple domains and robustness to compression. We propose a detection approach by capturing frame inconsistency that broadly exists in different forgery techniques. We introduce a temporally-preserved module method to introduce spatial noise perturbations, directing the model's attention towards temporal information.
  arXiv  Detail & Related papers  (2023-11-20T06:04:09Z)
• Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption [94.5031244215761]
  We propose to boost the generalization of deepfake detection by distinguishing the "regularity disruption" that does not appear in real videos. Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator. Such practice allows us to achieve deepfake detection without using fake videos and improves the generalization ability in a simple and efficient manner.
  arXiv  Detail & Related papers  (2022-07-21T10:42:34Z)
• Implicit Motion Handling for Video Camouflaged Object Detection [60.98467179649398]
  We propose a new video camouflaged object detection (VCOD) framework. It can exploit both short-term and long-term temporal consistency to detect camouflaged objects from video frames.
  arXiv  Detail & Related papers  (2022-03-14T17:55:41Z)
• Video Salient Object Detection via Contrastive Features and Attention Modules [106.33219760012048]
  We propose a network with attention modules to learn contrastive features for video salient object detection. A co-attention formulation is utilized to combine the low-level and high-level features. We show that the proposed method requires less computation, and performs favorably against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-03T17:40:32Z)
• Spatio-temporal Features for Generalized Detection of Deepfake Videos [12.453288832098314]
  We propose-temporal features, modeled by 3D CNNs, to extend the capabilities to detect new sorts of deep videos. We show that our approach outperforms existing methods in terms of generalization capabilities.
  arXiv  Detail & Related papers  (2020-10-22T16:28:50Z)

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.