Present and Future Generalization of Synthetic Image Detectors

• URL: http://arxiv.org/abs/2409.14128v1
• Date: Sat, 21 Sep 2024 12:46:17 GMT
• Title: Present and Future Generalization of Synthetic Image Detectors
• Authors: Pablo Bernabeu-Perez, Enrique Lopez-Cuena, Dario Garcia-Gasulla,
• Abstract summary: Detectors need to be able to generalize widely and be robust to uncontrolled alterations. None of the evaluated detectors is found universal, but results indicate an ensemble could be. Experiments on data collected in the wild show this task to be more challenging than the one defined by large-scale datasets.
• Score: 0.6144680854063939
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The continued release of new and better image generation models increases the demand for synthetic image detectors. In such a dynamic field, detectors need to be able to generalize widely and be robust to uncontrolled alterations. The present work is motivated by this setting, when looking at the role of time, image transformations and data sources, for detector generalization. In these experiments, none of the evaluated detectors is found universal, but results indicate an ensemble could be. Experiments on data collected in the wild show this task to be more challenging than the one defined by large-scale datasets, pointing to a gap between experimentation and actual practice. Finally, we observe a race equilibrium effect, where better generators lead to better detectors, and vice versa. We hypothesize this pushes the field towards a perpetually close race between generators and detectors.

Related papers

• Zero-Shot Detection of AI-Generated Images [54.01282123570917]
  We propose a zero-shot entropy-based detector (ZED) to detect AI-generated images. Inspired by recent works on machine-generated text detection, our idea is to measure how surprising the image under analysis is compared to a model of real images. ZED achieves an average improvement of more than 3% over the SoTA in terms of accuracy.
  arXiv  Detail & Related papers  (2024-09-24T08:46:13Z)
• 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)
• Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets [6.554757265434464]
  Many datasets for AI-generated image detection contain biases related to JPEG compression and image size. We demonstrate that detectors indeed learn from these undesired factors. It leads to more than 11 percentage points increase in cross-generator performance for ResNet50 and Swin-T detectors.
  arXiv  Detail & Related papers  (2024-03-26T11:39:00Z)
• GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning [50.7702397913573]
  The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology. We propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection.
  arXiv  Detail & Related papers  (2024-02-03T03:13:50Z)
• GenDet: Towards Good Generalizations for AI-Generated Image Detection [27.899521298845357]
  Existing methods can effectively detect images generated by seen generators, but it is challenging to detect those generated by unseen generators. This paper addresses the unseen-generator detection problem by considering this task from the perspective of anomaly detection. Our method encourages smaller output discrepancies between the student and the teacher models for real images while aiming for larger discrepancies for fake images.
  arXiv  Detail & Related papers  (2023-12-12T11:20:45Z)
• Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation [76.45506517198956]
  Object detection in low-light scenarios has attracted much attention in the past few years. A mainstream and representative scheme introduces enhancers as the pre-processing for regular detectors. In this work, we try to arouse the potential of enhancer + detector.
  arXiv  Detail & Related papers  (2023-09-07T08:11:47Z)
• SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes [7.553507857251396]
  We propose a novel deepfake detector, called SeeABLE, that formalizes the detection problem as a (one-class) out-of-distribution detection task. SeeABLE pushes perturbed faces towards predefined prototypes using a novel regression-based bounded contrastive loss. We show that our model convincingly outperforms competing state-of-the-art detectors, while exhibiting highly encouraging generalization capabilities.
  arXiv  Detail & Related papers  (2022-11-21T09:38:30Z)
• 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)
• Ensembling with Deep Generative Views [72.70801582346344]
  generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose. Here, we investigate whether such views can be applied to real images to benefit downstream analysis tasks such as image classification. We use StyleGAN2 as the source of generative augmentations and investigate this setup on classification tasks involving facial attributes, cat faces, and cars.
  arXiv  Detail & Related papers  (2021-04-29T17:58:35Z)

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.