arXiv 2506.008742025-06-01cs.CV

打破检测器中潜在先验偏差以实现可泛化的AIGC图像检测

Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection

Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, and SZU-AFS Joint Innovation Center for AI Technology（广东智能信息处理省级重点实验室、深圳媒体安全重点实验室及SZU-AFS人工智能技术联合创新中心）；Nanchang University（南昌大学）；University of North Texas（北卡罗来纳州立大学）

Yue Zhou, Xinan He, KaiQing Lin, Bin Fan, Feng Ding, Bin Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出流形上对抗训练（OMAT），通过优化扩散模型初始潜在噪声生成流形上对抗样本，打破检测器的潜在先验偏差，并引入GenImage++基准，显著提升AIGC检测器的跨生成器泛化能力。

摘要：

当前的AIGC检测器在由训练所用的同一生成器产生的图像上往往能达到接近完美的准确率，但在泛化到未见过的生成器输出时却表现困难。我们将这一失败部分归因于潜在先验偏差：检测器学习到的捷径与源自初始噪声向量的模式相关，而不是学习鲁棒的生成伪影。为了解决这一问题，我们提出了流形上对抗训练（OMAT）：通过在固定条件约束下优化扩散模型的初始潜在噪声，我们生成保持在生成器输出流形上的流形上对抗样本——不同于像素空间攻击，后者会引入生成器自身无法再现的偏离流形的扰动，并可能掩盖真正的判别性伪影。为了针对最先进的生成模型进行测试，我们引入了GenImage++，这是一个仅用于测试的基准，包含来自先进生成器（Flux.1、SD3）的输出，并具有扩展提示词和多样化风格。我们将该对抗训练范式应用于ResNet50和CLIP基线，并在现有的AIGC取证基准和近期挑战数据集上进行评估。大量实验表明，经过对抗训练的检测器在无需任何网络重新设计的情况下显著提升了跨生成器性能。我们关于潜在先验偏差的发现为未来的数据集构建和检测器评估提供了有价值的见解，指导开发更鲁棒且更具泛化能力的AIGC取证方法。

英文摘要：

Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators. We trace this failure in part to latent prior bias: detectors learn shortcuts tied to patterns stemming from the initial noise vector rather than learning robust generative artifacts. To address this, we propose On-Manifold Adversarial Training (OMAT): by optimizing the initial latent noise of diffusion models under fixed conditioning, we generate on-manifold adversarial examples that remain on the generator's output manifold-unlike pixel-space attacks, which introduce off-manifold perturbations that the generator itself cannot reproduce and that can obscure the true discriminative artifacts. To test against state-of-the-art generative models, we introduce GenImage++, a test-only benchmark of outputs from advanced generators (Flux.1, SD3) with extended prompts and diverse styles. We apply our adversarial-training paradigm to ResNet50 and CLIP baselines and evaluate across existing AIGC forensic benchmarks and recent challenge datasets. Extensive experiments show that adversarially trained detectors significantly improve cross-generator performance without any network redesign. Our findings on latent-prior bias offer valuable insights for future dataset construction and detector evaluation, guiding the development of more robust and generalizable AIGC forensic methodologies.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。