Spectral Tail Auxiliary Learning for AI-Generated Image Detection

• URL: http://arxiv.org/abs/2605.22751v1
• Date: Thu, 21 May 2026 17:20:59 GMT
• Title: Spectral Tail Auxiliary Learning for AI-Generated Image Detection
• Abstract summary: We propose Spectral Tail Auxiliary Learning (STAL) for generalizable AI-generated image detection.<n>STAL transfers spectral-tail cues from a tail-aware frequency teacher to a spatial detector during training, while all frequency-domain modules are discarded at inference time.<n>STAL achieves strong generalization and stability across generators, data distributions, and real-world scenarios.
• Score: 30.7508235642367
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. Many existing methods exploit frequency-domain cues for detection, typically described as frequency-domain artifacts or high-frequency discrepancies. However, the specific and recurring spectral regularities remain insufficiently understood and characterized. In this paper, we systematically analyze the one-dimensional radial log-power spectra of real and generated images. We find that generated images do not necessarily exhibit higher or lower energy across the entire spectrum or high-band range. Instead, their spectra deviate from the power-law decay and show an anomalous uplift in the ultra-high-frequency tail. We term this phenomenon spectral tail uplift. We further attribute this phenomenon to nonlinear harmonic accumulation in trained generative models, suggesting that it can serve as a structural cue across generative architectures. Based on this observation, we propose Spectral Tail Auxiliary Learning (STAL), a frequency-domain auxiliary supervision framework for generalizable AI-generated image detection. STAL transfers spectral-tail cues from a tail-aware frequency teacher to a spatial detector during training, while all frequency-domain modules are discarded at inference time. Consequently, STAL introduces no inference overhead. Extensive experiments on 9 public datasets show that STAL achieves strong generalization and stability across generators, data distributions, and real-world scenarios.

Related papers

• AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors [10.352581041881864]
  This paper introduces AnyBand-Diff, a spectral-prior-guided diffusion framework tailored for robust spectral reconstruction.<n>To ensure radiometric fidelity, a Physics-Guided Sampling mechanism is proposed.<n>Experiments confirm the effectiveness of AnyBand-Diff in generating reliable imagery.
  arXiv  Detail & Related papers  (2026-05-14T04:04:34Z)
• Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging [79.35520607451187]
  We propose Phy-CoSF, which synergizes deep unfolding networks with implicit neural representations.<n>Specifically, we propose a two-phase architecture that bridges discrete-wavelength training with continuous spectral rendering.
  arXiv  Detail & Related papers  (2026-05-13T14:17:02Z)
• FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks [5.215187965365735]
  We show that models tend to fit low-frequency signals before high-frequency ones.<n>We propose the FreLE algorithm, which enhances model generalization through both explicit and implicit frequency regularization.
  arXiv  Detail & Related papers  (2025-10-29T03:22:51Z)
• Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing [92.61216319417208]
  We propose a novel frequency domain-based diffusion model, named ours, for fully exploiting the beneficial knowledge in unpaired clear data.<n>Inspired by the strong generative ability shown by Diffusion Models (DMs), we tackle the dehazing task from the perspective of frequency domain reconstruction.
  arXiv  Detail & Related papers  (2025-07-02T01:22:46Z)
• LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputation [55.800319453296886]
  Time series with missing or irregularly sampled data are a persistent challenge in machine learning.<n>We introduce a different Lombiable--Scargle layer that enables a reliable computation of the power spectrum of irregularly sampled data.
  arXiv  Detail & Related papers  (2025-06-20T14:48:42Z)
• CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis [69.02751635551724]
  Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding.<n> variability in channel dimensionality and captured wavelengths among spectral cameras impede the development of AI-driven methodologies.<n>We introduce CARL, a model for Camera-Agnostic Representation Learning across RGB, multispectral, and hyperspectral imaging modalities.
  arXiv  Detail & Related papers  (2025-04-27T13:06:40Z)
• Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum [38.302088844940556]
  We propose a novel detection method based on the fractal self-similarity of the spectrum.<n>We show that AI-generated images exhibit fractal-like spectral growth through periodic extension and low-pass filtering.<n>Our method mitigates the impact of varying spectral characteristics across different generators, improving detection performance for images from unseen models.
  arXiv  Detail & Related papers  (2025-03-11T14:37:06Z)
• Any-Resolution AI-Generated Image Detection by Spectral Learning [36.562914181733426]
  We build upon the key idea that the spectral distribution of real images constitutes both an invariant and highly discriminative pattern for AI-generated image detection.<n>Our approach achieves a 5.5% absolute improvement in AUC over the previous state-of-the-art across 13 recent generative approaches.
  arXiv  Detail & Related papers  (2024-11-28T23:55:19Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization [67.47895278233717]
  We develop a progressive frequency regularization technique to tackle the over-reconstruction issue within the frequency space. FreGS achieves superior novel view synthesis and outperforms the state-of-the-art consistently.
  arXiv  Detail & Related papers  (2024-03-11T17:00:27Z)
• Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile [15.5188527312094]
  We propose a framework to mitigate the disparity in frequency domain of the generated images. This is realized by spectrum translation for the refinement of image generation (STIG) based on contrastive learning. We evaluate our framework across eight fake image datasets and various cutting-edge models to demonstrate the effectiveness of STIG.
  arXiv  Detail & Related papers  (2024-03-08T06:39:24Z)

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.