arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09231cs.CV
收藏

针对糖尿病视网膜病变图像分级系统的对抗性曝光攻击

Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading

Nanyang Technological University(南洋理工大学);Institute of High Performance Computing(高性能计算研究所);Centre for Frontier AI Research(前沿人工智能研究中心);Agency for Science, Technology and Research(新加坡科学技术研究局);New York University(纽约大学);Singapore Institute of Technology(新加坡理工学院)

Yupeng Cheng, Qing Guo, Felix Juefei-Xu, Huazhu Fu, Shang-Wei Lin, Weisi Lin

AI总结:

本文提出对抗性曝光攻击方法,通过生成自然曝光图像误导最先进的深度神经网络,揭示了糖尿病视网膜病变自动分级系统的潜在威胁并促进鲁棒性研究。

摘要:

糖尿病视网膜病变(DR)是全球视力丧失的主要原因之一。为辅助诊断,大量前沿研究构建了强大的深度神经网络(DNNs),通过视网膜眼底图像(RFIs)自动对DR进行分级。然而,RFIs常受相机曝光问题影响,可能导致分级错误。错误分级结果可能给病情恶化带来高风险。本文从对抗攻击视角研究此问题。我们识别并引入了一种全新任务的解决方案,称为对抗性曝光攻击,能够生成自然的曝光图像并误导最先进的DNNs。我们在真实世界的公开DR数据集上使用三种DNNs(如ResNet50、MobileNet和EfficientNet)验证了所提方法,证明该方法在攻击迁移中实现了高图像质量和成功率。该方法揭示了基于DNN的自动DR分级面临的潜在威胁,将有助于未来开发对曝光鲁棒的DR分级方法。

英文摘要:

Diabetic Retinopathy (DR) is a leading cause of vision loss around the world. To help diagnose it, numerous cutting-edge works have built powerful deep neural networks (DNNs) to automatically grade DR via retinal fundus images (RFIs). However, RFIs are commonly affected by camera exposure issues that may lead to incorrect grades. The mis-graded results can potentially pose high risks to an aggravation of the condition. In this paper, we study this problem from the viewpoint of adversarial attacks. We identify and introduce a novel solution to an entirely new task, termed as adversarial exposure attack, which is able to produce natural exposure images and mislead the state-of-the-art DNNs. We validate our proposed method on a real-world public DR dataset with three DNNs, e.g., ResNet50, MobileNet, and EfficientNet, demonstrating that our method achieves high image quality and success rate in transferring the attacks. Our method reveals the potential threats to DNN-based automatic DR grading and would benefit the development of exposure-robust DR grading methods in the future.

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。

↑