Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection

• URL: http://arxiv.org/abs/2510.05633v1
• Date: Tue, 07 Oct 2025 07:33:47 GMT
• Title: Beyond Spectral Peaks: Interpreting the Cues Behind Synthetic Image Detection
• Authors: Sara Mandelli, Diego Vila-Portela, David Vázquez-Padín, Paolo Bestagini, Fernando Pérez-González,
• Abstract summary: State-of-the-art detectors are typically used as black-boxes, and it still remains unclear whether they truly rely on these peaks.<n>We propose a strategy to remove spectral peaks from images and analyze the impact of this operation on several detectors.<n>In addition, we introduce a simple linear detector that relies exclusively on frequency peaks, providing a fully interpretable baseline free from the confounding influence of deep learning.
• Score: 48.54857325137626
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the years, the forensics community has proposed several deep learning-based detectors to mitigate the risks of generative AI. Recently, frequency-domain artifacts (particularly periodic peaks in the magnitude spectrum), have received significant attention, as they have been often considered a strong indicator of synthetic image generation. However, state-of-the-art detectors are typically used as black-boxes, and it still remains unclear whether they truly rely on these peaks. This limits their interpretability and trust. In this work, we conduct a systematic study to address this question. We propose a strategy to remove spectral peaks from images and analyze the impact of this operation on several detectors. In addition, we introduce a simple linear detector that relies exclusively on frequency peaks, providing a fully interpretable baseline free from the confounding influence of deep learning. Our findings reveal that most detectors are not fundamentally dependent on spectral peaks, challenging a widespread assumption in the field and paving the way for more transparent and reliable forensic tools.

Related papers

• Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection [30.53429368921365]
  A critical limitation of current detectors is their failure to generalize to images from unseen generative models.<n>We introduce a simple yet remarkably effective pixel-level mapping pre-processing step to disrupt the pixel value distribution of images.<n>We show that our approach significantly boosts the cross-generator performance of state-of-the-art detectors.
  arXiv  Detail & Related papers  (2025-12-19T08:47:09Z)
• Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection [25.546882596181337]
  Generalizability and robustness are two critical concerns of a forgery detector.<n>We propose a two-step frequency alignment method to remove the frequency discrepancy between real and fake images.
  arXiv  Detail & Related papers  (2025-11-25T03:45:35Z)
• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors [58.75916798814376]
  We develop a few-shot anomaly detector termed FoundAD.<n>We observe that the anomaly amount in an image directly correlates with the difference in the learnt embeddings.<n>The simple operator acts as an effective tool for anomaly detection to characterize and identify out-of-distribution regions in an image.
  arXiv  Detail & Related papers  (2025-10-02T11:53:20Z)
• Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control [5.231219025536678]
  Methods for hyperspectral pansharpening often overlook the unique challenges posed by hyperspectral data fusion.<n>A single lightweight neural network is used, with weights that adapt on the fly to each band.<n>The proposed method is fully unsupervised, with no prior training on external data, flexible, and low-complexity.
  arXiv  Detail & Related papers  (2025-05-22T13:24:24Z)
• Correct Estimation of Higher-Order Spectra: From Theoretical Challenges to Practical Multi-Channel Implementation in SignalSnap [0.0]
  Higher-order spectra offer powerful methods for solving critical problems in signal processing and data analysis.<n>Their practical use has remained limited due to unresolved mathematical issues in spectral estimation.<n>We introduce quasi-polyspectra to uncover non-stationary, time-dependent higher-order features.<n>We implement these new estimators in SignalSnap, an open-source GPU-accelerated library capable of efficiently analyzing datasets exceeding hundreds of gigabytes within minutes.
  arXiv  Detail & Related papers  (2025-05-02T12:36:30Z)
• 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)
• On the Frequency Bias of Generative Models [61.60834513380388]
  We analyze proposed measures against high-frequency artifacts in state-of-the-art GAN training. We find that none of the existing approaches can fully resolve spectral artifacts yet. Our results suggest that there is great potential in improving the discriminator.
  arXiv  Detail & Related papers  (2021-11-03T18:12:11Z)
• Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis [69.09526348527203]
  Deep generative models have led to highly realistic media, known as deepfakes, that are commonly indistinguishable from real to human eyes. We propose a novel fake detection that is designed to re-synthesize testing images and extract visual cues for detection. We demonstrate the improved effectiveness, cross-GAN generalization, and robustness against perturbations of our approach in a variety of detection scenarios.
  arXiv  Detail & Related papers  (2021-05-29T21:22:24Z)
• Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain [88.7339322596758]
  We present a novel Spatial-Phase Shallow Learning (SPSL) method, which combines spatial image and phase spectrum to capture the up-sampling artifacts of face forgery. SPSL can achieve the state-of-the-art performance on cross-datasets evaluation as well as multi-class classification and obtain comparable results on single dataset evaluation.
  arXiv  Detail & Related papers  (2021-03-02T16:45:08Z)
• A Review of 1D Convolutional Neural Networks toward Unknown Substance Identification in Portable Raman Spectrometer [0.0]
  Raman spectroscopy is a powerful analytical tool with applications ranging from quality control to cutting edge biomedical research. They have been adopted widely by first responders and law enforcement agencies for the field analysis of unknown substances. Field detection and identification of unknown substances with Raman spectroscopy rely heavily on the spectral matching capability of the devices on hand.
  arXiv  Detail & Related papers  (2020-06-18T14:28:00Z)

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.