Exposing and Mitigating Temporal Attack in Deepfake Video Detection

• URL: http://arxiv.org/abs/2605.07398v1
• Date: Fri, 08 May 2026 07:53:57 GMT
• Title: Exposing and Mitigating Temporal Attack in Deepfake Video Detection
• Abstract summary: deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks.<n>To mitigate this vulnerability we propose SpInShield, a temporal spectral-invariant defense framework.
• Score: 16.98377521260699
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit on fragile temporal spectrum cues, rather than learning robust semantic causality. To mitigate this vulnerability, we propose SpInShield, a temporal spectral-invariant defense framework explicitly designed to decouple semantic motion from manipulatable spectral artifacts. We propose a learnable spectral adversary that dynamically synthesizes severe spectral deformations, simulating extreme attack scenarios. By employing a shortcut suppression optimization strategy, SpInShield compels the encoder to extract reliable forensic cues while purging unstable spectral statistics from the latent space. Experiments show that SpInShield obtains competitive performance on widely used datasets and outperforms the strongest baseline by 21.30 percentage points in AUC under simulated amplitude spectral attacks.

Related papers

• Full spectrum Unlearnable Examples via Spectral Equalization [29.22443621401928]
  We propose Full-spectrum Unlearnable examples via Spectral Equalization (FUSE)<n>FUSE generates spectrum-agnostic perturbations by equalizing the contributions from different bands and enforcing cross-band consistency.<n>Experiments across multiple datasets, architectures, and spectral filtering demonstrate the strong protection achieved by FUSE.
  arXiv  Detail & Related papers  (2026-06-25T07:53:53Z)
• SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition [49.508770157706486]
  We propose SRENet to learn both global context and fine-grained temporal dynamics of motion from a frequency perspective for action recognition.<n>SRENet achieves state-of-the-art performance, validating the effectiveness of frequency modeling in point cloud-based action understanding.
  arXiv  Detail & Related papers  (2026-06-02T05:11:47Z)
• Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting [21.300422393514804]
  We propose a deterministic framework that reformulates nowcasting as progressive frequency-decoupled refinement.<n>SDIR first extracts a stable low-frequency synoptic skeleton, then iteratively refines high-frequency textures under physical constraints.<n> Experiments on three benchmarks show SDIR significantly outperforms SOTA methods in spatial accuracy.
  arXiv  Detail & Related papers  (2026-06-01T07:34:30Z)
• Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition [29.049635093468456]
  Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications.<n> patch-based and texture-based attacks pose real threats to security-critical applications such as person detection in surveillance and autonomous systems.<n>We propose Adversarial Spectrum Defense (ASD) to analyze adversarial patterns across multiple frequency scales.
  arXiv  Detail & Related papers  (2026-04-12T16:24:08Z)
• Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting [63.29941651174379]
  3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface.<n>This attack poisons training images, excessively inducing Gaussian growth to cause resource exhaustion.<n>We propose textbfSpectral Defense in Gaussian and image fields.
  arXiv  Detail & Related papers  (2026-03-13T08:56:49Z)
• Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP [68.44229678548298]
  Contrastive Spectral Rectification (CSR) is an efficient test-time defense against adversarial examples.<n>CSR outperforms the SOTA by an average of 18.1% against strong AutoAttack.<n>CSR exhibits broad applicability across diverse visual tasks.
  arXiv  Detail & Related papers  (2026-01-27T05:24:45Z)
• Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks [48.911832772464145]
  Contrastive learning (CL) has recently gained prominence in the domain of recommender systems. This paper identifies a vulnerability of CL-based recommender systems that they are more susceptible to poisoning attacks aiming to promote individual items.
  arXiv  Detail & Related papers  (2023-11-30T04:25:28Z)
• Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection [6.713879688002623]
  Existing anti-spoofing methods often simulate specific attack types, such as synthetic or replay attacks. Current unified solutions struggle to detect spoofing artifacts. We present a spectra-temporal fusion leveraging frame-level and utterance-level coefficients.
  arXiv  Detail & Related papers  (2023-09-18T14:54:42Z)
• Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms [19.514932118278523]
  We propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset.
  arXiv  Detail & Related papers  (2023-08-18T04:51:15Z)
• A Spectral Perspective towards Understanding and Improving Adversarial Robustness [8.912245110734334]
  adversarial training (AT) has proven to be an effective defense approach, but mechanism for robustness improvement is not fully understood. We show that AT induces the deep model to focus more on the low-frequency region, which retains the shape-biased representations, to gain robustness. We propose a spectral alignment regularization (SAR) such that the spectral output inferred by an attacked adversarial input stays as close as possible to its natural input counterpart.
  arXiv  Detail & Related papers  (2023-06-25T14:47:03Z)
• Spatial-Frequency Discriminability for Revealing Adversarial Perturbations [53.279716307171604]
  Vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. Current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. We propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition.
  arXiv  Detail & Related papers  (2023-05-18T10:18:59Z)
• Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction [127.20208645280438]
  Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. Mask-guided Spectral-wise Transformer (MST) proposes a novel framework for HSI reconstruction.
  arXiv  Detail & Related papers  (2021-11-15T16:59:48Z)
• Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems [78.5097679815944]
  This paper introduces a defense approach against end-to-end adversarial attacks developed for cutting-edge speech-to-text systems. First, we represent speech signals with 2D spectrograms using the short-time Fourier transform. Second, we iteratively find a safe vector using a spectrogram subspace projection operation. Third, we synthesize a spectrogram with such a safe vector using a novel GAN architecture trained with Sobolev integral probability metric.
  arXiv  Detail & Related papers  (2021-03-15T01:11:13Z)

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.