Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
- URL: http://arxiv.org/abs/2403.17608v2
- Date: Thu, 28 Mar 2024 15:24:16 GMT
- Title: Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
- Authors: Patrick Grommelt, Louis Weiss, Franz-Josef Pfreundt, Janis Keuper,
- Abstract summary: 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.
- Score: 6.554757265434464
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors. In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size. Using the GenImage dataset, we demonstrate that detectors indeed learn from these undesired factors. Furthermore, we show that removing the named biases substantially increases robustness to JPEG compression and significantly alters the cross-generator performance of evaluated detectors. Specifically, it leads to more than 11 percentage points increase in cross-generator performance for ResNet50 and Swin-T detectors on the GenImage dataset, achieving state-of-the-art results. We provide the dataset and source codes of this paper on the anonymous website: https://www.unbiased-genimage.org
Related papers
- A Bias-Free Training Paradigm for More General AI-generated Image Detection [15.421102443599773]
A well-designed forensic detector should detect generator specific artifacts rather than reflect data biases.
We propose B-Free, a bias-free training paradigm, where fake images are generated from real ones.
We show significant improvements in both generalization and robustness over state-of-the-art detectors.
arXiv Detail & Related papers (2024-12-23T15:54:32Z) - Is JPEG AI going to change image forensics? [50.92778618091496]
We investigate the counter-forensic effects of the forthcoming JPEG AI standard based on neural image compression.
We show that an increase in false alarms impairs the performance of leading forensic detectors when analyzing genuine content processed through JPEG AI.
arXiv Detail & Related papers (2024-12-04T12:07:20Z) - 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.
In this paper, we investigate how detection performance varies across model backbones, types, and datasets.
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) - Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors [62.63467652611788]
We introduce SEMI-TRUTHS, featuring 27,600 real images, 223,400 masks, and 1,472,700 AI-augmented images.
Each augmented image is accompanied by metadata for standardized and targeted evaluation of detector robustness.
Our findings suggest that state-of-the-art detectors exhibit varying sensitivities to the types and degrees of perturbations, data distributions, and augmentation methods used.
arXiv Detail & Related papers (2024-11-12T01:17:27Z) - 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) - Improving Interpretability and Robustness for the Detection of AI-Generated Images [6.116075037154215]
We analyze existing state-of-the-art AIGI detection methods based on frozen CLIP embeddings.
We show how to interpret them, shedding light on how images produced by various AI generators differ from real ones.
arXiv Detail & Related papers (2024-06-21T10:33:09Z) - 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) - Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement [30.698359275889363]
A surge in scientific publications suspected of image manipulation has led to numerous retractions.
Image splicing detection is more challenging due to the lack of reference images and the typically small tampered areas.
We propose an Uncertainty-guided Refinement Network (URN) to mitigate the impact of disruptive factors.
arXiv Detail & Related papers (2023-09-28T12:36:12Z) - GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image [28.38575401686718]
We introduce the GenImage dataset, which includes over one million pairs of AI-generated fake images and collected real images.
The advantages allow the detectors trained on GenImage to undergo a thorough evaluation and demonstrate strong applicability to diverse images.
We conduct a comprehensive analysis of the dataset and propose two tasks for evaluating the detection method in resembling real-world scenarios.
arXiv Detail & Related papers (2023-06-14T15:21:09Z) - 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)
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.