政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/138287

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | Items with full text/Total items : 113656/144643 (79%)
Visitors : 51718015 Online Users : 601

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer

政大機構典藏 > 資訊學院 > 資訊科學系 > 會議論文 > Item 140.119/138287

Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/138287

Title:	Defense against N-pixel Attacks based on Image Reconstruction
Authors:	左瑞麟 Tso, Raylin Liu, Zi-Yuan Wang, Peter Shaojui Hsiao, Shou-Ching
Contributors:	資科系
Keywords:	Adversarial Examples;N-pixel Attacks;Image Reconstruction;Defense
Date:	2020-10
Issue Date:	2021-12-09 16:09:27 (UTC+8)
Abstract:	Since machine learning and deep learning are largely used for image recognition in real-world applications, how to avoid adversarial attacks become an important issue. It is common that attackers add adversarial perturbation to a normal image in order to fool the models. The N-pixel attack is one of the recently popular adversarial methods by simply changing a few pixels in the image. We observe that changing the few pixels leads to an obvious difference with its neighboring pixels. Therefore, this research aims to defend the N-pixel attacks based on image reconstruction. We develop a three-staged reconstructing algorithm to recover the fooling images. Experimental results show that the accuracy of CIFAR-10 test dataset can reach 92% after applying our proposed algorithm, indicating that the algorithm can maintain the original inference accuracy on normal dataset. Besides, the effectiveness of defending N-pixel attacks is also validated by reconstructing 500 attacked images using the proposed algorithm. The results show that we have a 90% to 92% chance of successful defense, where N=1,3,5,10,and 15.
Relation:	SBC `20: Proceedings of the 8th International Workshop on Security in Blockchain and Cloud Computing, pp.3-7
Data Type:	conference
DOI 連結:	https://doi.org/10.1145/3384942.3406867
DOI:	10.1145/3384942.3406867
Appears in Collections:	[資訊科學系] 會議論文

Files in This Item:

File	Size	Format
21.pdf	2507Kb	Adobe PDF2	293	View/Open

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

Loading...