Deepfake Detection with Multi-Artifact Subspace Fine-Tuning and Selective Layer Masking

• URL: http://arxiv.org/abs/2601.01041v1
• Date: Sat, 03 Jan 2026 02:33:18 GMT
• Title: Deepfake Detection with Multi-Artifact Subspace Fine-Tuning and Selective Layer Masking
• Authors: Xiang Zhang, Wenliang Weng, Daoyong Fu, Ziqiang Li, Zhangjie Fu,
• Abstract summary: Deepfake detection still faces significant challenges in cross-dataset and real-world complex scenarios.<n>This paper proposes a deepfake detection method based on Multi-Artifact Subspaces and selective layer masks (MASM)<n>MASM explicitly decouples semantic representations from artifact representations and constrains the fitting strength of artifact subspaces.
• Score: 11.158258169109907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deepfake detection still faces significant challenges in cross-dataset and real-world complex scenarios. The root cause lies in the high diversity of artifact distributions introduced by different forgery methods, while pretrained models tend to disrupt their original general semantic structures when adapting to new artifacts. Existing approaches usually rely on indiscriminate global parameter updates or introduce additional supervision signals, making it difficult to effectively model diverse forgery artifacts while preserving semantic stability. To address these issues, this paper proposes a deepfake detection method based on Multi-Artifact Subspaces and selective layer masks (MASM), which explicitly decouples semantic representations from artifact representations and constrains the fitting strength of artifact subspaces, thereby improving generalization robustness in cross-dataset scenarios. Specifically, MASM applies singular value decomposition to model weights, partitioning pretrained weights into a stable semantic principal subspace and multiple learnable artifact subspaces. This design enables decoupled modeling of different forgery artifact patterns while preserving the general semantic subspace. On this basis, a selective layer mask strategy is introduced to adaptively regulate the update behavior of corresponding network layers according to the learning state of each artifact subspace, suppressing overfitting to any single forgery characteristic. Furthermore, orthogonality constraints and spectral consistency constraints are imposed to jointly regularize multiple artifact subspaces, guiding them to learn complementary and diverse artifact representations while maintaining a stable overall spectral structure.

Related papers

• Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing [24.03278912134978]
  We propose Any Optical Model (AOM) to accommodate arbitrary band compositions, sensor types, and resolution scales.<n>AOM consistently achieves state-of-the-art (SOTA) performance under challenging conditions such as band missing, cross sensor, and cross resolution settings.
  arXiv  Detail & Related papers  (2025-12-19T04:21:01Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• MAGIC: Mask-Guided Diffusion Inpainting with Multi-Level Perturbations and Context-Aware Alignment for Few-Shot Anomaly Generation [4.773905705768453]
  Few-shot anomaly generation is emerging as a practical solution for augmenting the scarce anomaly data in industrial quality control settings.<n>We propose MAGIC-Mask-guided inpainting with multi-level perturbations and Context-aware alignment.<n> MAGIC outperforms previous state-of-the-arts in downstream anomaly tasks.
  arXiv  Detail & Related papers  (2025-07-03T04:54:37Z)
• Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction [20.1863553357121]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies various dense prediction tasks and diverse semantic class predictions.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection [57.646582245834324]
  We propose a simple yet effective deepfake detector called LSDA. It is based on a idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary. We show that our proposed method is surprisingly effective and transcends state-of-the-art detectors across several widely used benchmarks.
  arXiv  Detail & Related papers  (2023-11-19T09:41:10Z)
• Siamese Transition Masked Autoencoders as Uniform Unsupervised Visual Anomaly Detector [4.33060257697635]
  This paper proposes a novel framework termed Siamese Transition Masked Autoencoders(ST-MAE) to handle various visual anomaly detection tasks uniformly. Our deep feature transition scheme yields a nonsupervised and semantic self-supervisory task to extract normal patterns.
  arXiv  Detail & Related papers  (2022-11-01T09:45:49Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning [55.79997930181418]
  Generalized Zero-Shot Learning aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. We propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
  arXiv  Detail & Related papers  (2022-07-05T04:04:37Z)

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.