Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection

• URL: http://arxiv.org/abs/2311.11278v2
• Date: Thu, 28 Mar 2024 17:25:51 GMT
• Title: Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection
• Authors: Zhiyuan Yan, Yuhao Luo, Siwei Lyu, Qingshan Liu, Baoyuan Wu,
• Abstract summary: 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.
• Score: 57.646582245834324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly received explanation is the tendency of these detectors to be overfitted to forgery-specific artifacts, rather than learning features that are widely applicable across various forgeries. To address this issue, we propose a simple yet effective detector called LSDA (\underline{L}atent \underline{S}pace \underline{D}ata \underline{A}ugmentation), which is based on a heuristic idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary, thereby mitigating the overfitting of method-specific features (see Fig.~\ref{fig:toy}). Following this idea, we propose to enlarge the forgery space by constructing and simulating variations within and across forgery features in the latent space. This approach encompasses the acquisition of enriched, domain-specific features and the facilitation of smoother transitions between different forgery types, effectively bridging domain gaps. Our approach culminates in refining a binary classifier that leverages the distilled knowledge from the enhanced features, striving for a generalizable deepfake detector. Comprehensive experiments show that our proposed method is surprisingly effective and transcends state-of-the-art detectors across several widely used benchmarks.

Related papers

• Leveraging Mixture of Experts for Improved Speech Deepfake Detection [53.69740463004446]
  Speech deepfakes pose a significant threat to personal security and content authenticity. We introduce a novel approach for enhancing speech deepfake detection performance using a Mixture of Experts architecture.
  arXiv  Detail & Related papers  (2024-09-24T13:24:03Z)
• ED$^4$: Explicit Data-level Debiasing for Deepfake Detection [24.695989108814018]
  Learning intrinsic bias from limited data has been considered the main reason for the failure of deepfake detection with generalizability. We present ED$4$, a simple and effective strategy to address aforementioned biases explicitly at the data level. We conduct extensive experiments to demonstrate its effectiveness and superiority over existing deepfake detection approaches.
  arXiv  Detail & Related papers  (2024-08-13T10:05:20Z)
• COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection [56.7599217711363]
  Face forgery recognition methods can only process one face at a time. Most face forgery recognition methods can only process one face at a time. We propose COMICS, an end-to-end framework for multi-face forgery detection.
  arXiv  Detail & Related papers  (2023-08-03T03:37:13Z)
• 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)
• Controllable Guide-Space for Generalizable Face Forgery Detection [0.6445605125467573]
  We propose a controllable guide-space (GS) method to enhance the discrimination of different forgery domains. The well-designed guide-space can simultaneously achieve both the proper separation of forgery domains and the large distance between real-forgery domains.
  arXiv  Detail & Related papers  (2023-07-26T08:43:12Z)
• UCF: Uncovering Common Features for Generalizable Deepfake Detection [44.12640679000489]
  Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This paper presents a novel approach to address the two types of overfitting issues by uncovering common forgery features. Our framework can perform superior generalization than current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-27T04:07:29Z)
• MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection [11.124150983521158]
  We propose a novel framework named Multi-modal Contrastive Classification by Locally Correlated Representations. Our MC-LCR aims to amplify implicit local discrepancies between authentic and forged faces from both spatial and frequency domains. We achieve state-of-the-art performance and demonstrate the robustness and generalization of our method.
  arXiv  Detail & Related papers  (2021-10-07T09:24:12Z)
• Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark [53.9819155669618]
  This paper presents a large-scale dataset, named as PIDray, which covers various cases in real-world scenarios for prohibited item detection. With an intensive amount of effort, our dataset contains $12$ categories of prohibited items in $47,677$ X-ray images with high-quality annotated segmentation masks and bounding boxes. The proposed method performs favorably against the state-of-the-art methods, especially for detecting the deliberately hidden items.
  arXiv  Detail & Related papers  (2021-08-16T11:14:16Z)
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation [62.29076080124199]
  This paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains.
  arXiv  Detail & Related papers  (2020-03-23T13:40:06Z)

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.