arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2004.08443cs.CV
收藏

基于深度学习的拼接定位的对抗攻击

Adversarial Attack on Deep Learning-Based Splice Localization

Verisk Analytics;UCCS(科罗拉多大学科罗拉多斯普林斯分校)

Andras Rozsa, Zheng Zhong, Terrance E. Boult

摘要:

关于图像取证,研究人员已经提出了各种方法来检测和/或定位操作,例如拼接。最近表现最好的图像取证算法极大地受益于深度学习的应用,但这些工具可能容易受到对抗攻击的攻击。由于大多数提出的对抗性示例生成技术只能在端到端分类器上使用,因此尚未研究仅将深度学习用于特征提取的图像取证方法的对抗性鲁棒性。使用能够直接调整补丁的底层表示的新算法,我们在三个非端到端的基于深度学习的剪接定位工具上证明了通过对抗攻击隐藏图像操作是可行的。虽然测试的图像取证方法,EXIF-SC,SpliceRadar和Noiseprint,依赖于在不同的代理任务上训练的特征提取器,但我们发现,所形成的对抗性扰动可以在它们之间转移,因为它们的定位性能会恶化。

英文摘要:

Regarding image forensics, researchers have proposed various approaches to detect and/or localize manipulations, such as splices. Recent best performing image-forensics algorithms greatly benefit from the application of deep learning, but such tools can be vulnerable to adversarial attacks. Due to the fact that most of the proposed adversarial example generation techniques can be used only on end-to-end classifiers, the adversarial robustness of image-forensics methods that utilize deep learning only for feature extraction has not been studied yet. Using a novel algorithm capable of directly adjusting the underlying representations of patches we demonstrate on three non end-to-end deep learning-based splice localization tools that hiding manipulations of images is feasible via adversarial attacks. While the tested image-forensics methods, EXIF-SC, SpliceRadar, and Noiseprint, rely on feature extractors that were trained on different surrogate tasks, we find that the formed adversarial perturbations can be transferable among them regarding the deterioration of their localization performance.

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。

↑