Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples

• URL: http://arxiv.org/abs/2608.16646v1
• Date: Mon, 17 Aug 2026 14:45:53 GMT
• Title: Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples
• Abstract summary: We propose two novel attack methods targeted at detectors that leverage autoencoder reconstruction error.<n>We find that by constructing imperceptible adversarial examples, the distance between original and reconstruction can be artificially increased.<n>Our evaluation shows that detection performance is significantly decreased, even if attacked images additionally undergo real-world degradations.
• Score: 12.763640037752666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The impressive visual quality and ubiquity of AI-generated images call for reliable and robust detection methods. Reconstruction-based detectors have emerged as a promising direction for transparent and training-free identification of synthetic images. However, due to their fundamentally different mode of operation (compared to standard, classifier-based methods), little is known about their adversarial robustness. In this work, we propose two novel attack methods targeted at detectors that leverage autoencoder reconstruction error. We find that by constructing imperceptible adversarial examples, the distance between original and reconstruction can be artificially increased, causing fake images to be wrongly classified as real. Our evaluation including images from three state-of-the-art generators and three detectors demonstrates that detection performance is significantly decreased, even if attacked images additionally undergo real-world degradations. Critically, our adversarial examples naturally transfer across detectors, as they all share the same principle, pointing towards an inherent vulnerability of reconstruction-based detectors.

Related papers

• Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Images [32.470971087318695]
  We present a systematic evaluation of the adversarial robustness of three representative detectors across four diverse generative backbone models.<n>We construct adversarial attacks in white-box scenarios, which degrade the performance of all well-trained detectors.<n>We also find that attacks crafted against one detector can be transferred to others, indicating that adversarial attacks on detectors can also be constructed in a black-box setting.
  arXiv  Detail & Related papers  (2026-04-14T14:17:51Z)
• A Difference-in-Difference Approach to Detecting AI-Generated Images [12.73070476746517]
  Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones.<n>This raises concerns about their potential misuse and poses substantial challenges for detecting them.<n>We propose a novel difference-in-difference method for distinguishing real from fake images.
  arXiv  Detail & Related papers  (2026-02-27T06:57:39Z)
• ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack [56.0056378072843]
  We show that highly transferable adversarial images can be crafted solely via the upstream model.<n>We propose ForensicsSAM, a unified IFDL framework with built-in adversarial robustness.
  arXiv  Detail & Related papers  (2025-08-10T16:03:44Z)
• RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors [57.81012948133832]
  We present RAID (Robust evaluation of AI-generated image Detectors), a dataset of 72k diverse and highly transferable adversarial examples.<n>Our methodology generates adversarial images that transfer with a high success rate to unseen detectors.<n>Our findings indicate that current state-of-the-art AI-generated image detectors can be easily deceived by adversarial examples.
  arXiv  Detail & Related papers  (2025-06-04T14:16:00Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• 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)
• FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion [18.829659846356765]
  We propose a new synthetic image detector that uses features obtained by inverting an open-source pre-trained Stable Diffusion model. We show that these inversion features enable our detector to generalize well to unseen generators of high visual fidelity. We introduce a new challenging evaluation protocol that uses reverse image search to mitigate stylistic and thematic biases in the detector evaluation.
  arXiv  Detail & Related papers  (2024-06-12T19:14:58Z)
• ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction [29.370142078092375]
  Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets. We propose a novel epistemic UAD method, namely ReContrast, which optimize the entire network to reduce biases towards the pre-trained image domain. We conduct experiments across two popular industrial defect detection benchmarks and three medical image UAD tasks, which shows our superiority over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-05T05:21:15Z)
• Adversarially-Aware Robust Object Detector [85.10894272034135]
  We propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images. Our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images.
  arXiv  Detail & Related papers  (2022-07-13T13:59:59Z)
• Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving [87.3492357041748]
  In this paper, we showcase practical susceptibilities of multi-sensor detection by placing an adversarial object on top of a host vehicle. Our experiments demonstrate that successful attacks are primarily caused by easily corrupted image features. Towards more robust multi-modal perception systems, we show that adversarial training with feature denoising can boost robustness to such attacks significantly.
  arXiv  Detail & Related papers  (2021-01-17T21:15:34Z)
• Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise [25.85927871251385]
  anomaly detection relies on the reconstruction residual or, alternatively, on the reconstruction uncertainty. We consider an autoencoder architecture with skip connections to improve the sharpness of the reconstruction. We show that this model favors the reconstruction of clean images from arbitrary real-world images, regardless of the actual defects appearance.
  arXiv  Detail & Related papers  (2020-08-29T13:50:49Z)

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.