Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection

• URL: http://arxiv.org/abs/2511.19886v1
• Date: Tue, 25 Nov 2025 03:45:35 GMT
• Title: Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
• Authors: Chi Liu, Tianqing Zhu, Wanlei Zhou, Wei Zhao,
• Abstract summary: 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.
• Score: 25.546882596181337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As deep image forgery powered by AI generative models, such as GANs, continues to challenge today's digital world, detecting AI-generated forgeries has become a vital security topic. Generalizability and robustness are two critical concerns of a forgery detector, determining its reliability when facing unknown GANs and noisy samples in an open world. Although many studies focus on improving these two properties, the root causes of these problems have not been fully explored, and it is unclear if there is a connection between them. Moreover, despite recent achievements in addressing these issues from image forensic or anti-forensic aspects, a universal method that can contribute to both sides simultaneously remains practically significant yet unavailable. In this paper, we provide a fundamental explanation of these problems from a frequency perspective. Our analysis reveals that the frequency bias of a DNN forgery detector is a possible cause of generalization and robustness issues. Based on this finding, we propose a two-step frequency alignment method to remove the frequency discrepancy between real and fake images, offering double-sided benefits: it can serve as a strong black-box attack against forgery detectors in the anti-forensic context or, conversely, as a universal defense to improve detector reliability in the forensic context. We also develop corresponding attack and defense implementations and demonstrate their effectiveness, as well as the effect of the frequency alignment method, in various experimental settings involving twelve detectors, eight forgery models, and five metrics.

Related papers

• VAAS: Vision-Attention Anomaly Scoring for Image Manipulation Detection in Digital Forensics [0.0]
  Recent advances in AI-driven image generation have introduced new challenges for verifying the authenticity of digital evidence in forensic investigations.<n>Modern generative models can produce visually consistent forgeries that evade traditional detectors based on pixel or compression artefacts.<n>This paper introduces Vision-Attention Anomaly Scoring (VAAS), a novel dual-module framework that integrates global attention-based anomaly estimation.
  arXiv  Detail & Related papers  (2025-12-17T15:05:40Z)
• Transferable Dual-Domain Feature Importance Attack against AI-Generated Image Detector [32.543253278021446]
  Recent AI-generated image (AIGI) detectors achieve impressive accuracy under clean condition.<n>It is significant to develop advanced adversarial attacks for evaluating the security of such detectors.<n>This letter proposes a Dual-domain Feature Importance Attack scheme to invalidate AIGI detectors to some extent.
  arXiv  Detail & Related papers  (2025-11-19T16:03:15Z)
• Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective [22.514709685678813]
  We show that adversarial training (AT) suffers from performance collapse in AIGI detection.<n>Motivated by this difference, we propose Training-free Robust Detection via Information-theoretic Measures (TRIM)<n>TRIM builds on standard detectors and quantifies feature shifts using prediction entropy and KL divergence.
  arXiv  Detail & Related papers  (2025-05-28T17:20:49Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)
• Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection [96.539862328788]
  Existing forgery detection methods suffer from unsatisfactory generalization ability to determine the authenticity in the unseen domain. We propose a novel Attention Consistency Refined masked frequency forgery representation model toward generalizing face forgery detection algorithm (ACMF) Experiment results on several public face forgery datasets demonstrate the superior performance of the proposed method compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-07-21T08:58:49Z)
• 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)
• Discovering Transferable Forensic Features for CNN-generated Images Detection [100.12017277070576]
  We conduct the first analytical study to discover and understand transferable forensic features (T-FF) in universal detectors. In this work, we propose a novel forensic feature relevance statistic (FF-RS) to quantify and discover T-FF in universal detectors. Our investigations uncover an unexpected finding: color is a critical T-FF in universal detectors.
  arXiv  Detail & Related papers  (2022-08-24T07:48:07Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective [78.05383266222285]
  A human imperceptible perturbation can be generated to fool a deep neural network (DNN) for most images. A similar phenomenon has been observed in the deep steganography task, where a decoder network can retrieve a secret image back from a slightly perturbed cover image. We propose two new variants of universal perturbations: (1) Universal Secret Adversarial Perturbation (USAP) that simultaneously achieves attack and hiding; (2) high-pass UAP (HP-UAP) that is less visible to the human eye.
  arXiv  Detail & Related papers  (2021-02-12T12:26:39Z)

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.