Sukrut Rao (PhD Student)

Sukrut Sridhar Rao

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Location
E1 4 - 628
Phone
+49 681 9325 2028
Fax
+49 681 9325 2099

Publications

Rao, S., Stutz, D., & Schiele, B. (2020). Adversarial Training against Location-Optimized Adversarial Patches. Retrieved from https://arxiv.org/abs/2005.02313
(arXiv: 2005.02313)
Abstract
Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.
Export
BibTeX
@online{Rao_arXiv2005.02313, TITLE = {Adversarial Training against Location-Optimized Adversarial Patches}, AUTHOR = {Rao, Sukrut and Stutz, David and Schiele, Bernt}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/2005.02313}, EPRINT = {2005.02313}, EPRINTTYPE = {arXiv}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.}, }
Endnote
%0 Report %A Rao, Sukrut %A Stutz, David %A Schiele, Bernt %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Adversarial Training against Location-Optimized Adversarial Patches : %G eng %U http://hdl.handle.net/21.11116/0000-0007-80D0-C %U https://arxiv.org/abs/2005.02313 %D 2020 %X Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Cryptography and Security, cs.CR,Computer Science, Learning, cs.LG,Statistics, Machine Learning, stat.ML
Rao, S., Stutz, D., & Schiele, B. (2021). Adversarial Training Against Location-Optimized Adversarial Patches. In Computer Vision -- ECCV Workshops 2020. Glasgow, UK: Springer. doi:10.1007/978-3-030-68238-5_32
Export
BibTeX
@inproceedings{DBLP:conf/eccv/RaoSS20, TITLE = {Adversarial Training Against Location-Optimized Adversarial Patches}, AUTHOR = {Rao, Sukrut and Stutz, David and Schiele, Bernt}, LANGUAGE = {eng}, ISBN = {978-3-030-68237-8}, DOI = {10.1007/978-3-030-68238-5_32}, PUBLISHER = {Springer}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, DATE = {2021}, BOOKTITLE = {Computer Vision -- ECCV Workshops 2020}, EDITOR = {Bartoli, Adrian and Fusiello, Andrea}, PAGES = {429--448}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {12539}, ADDRESS = {Glasgow, UK}, }
Endnote
%0 Conference Proceedings %A Rao, Sukrut %A Stutz, David %A Schiele, Bernt %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Adversarial Training Against Location-Optimized Adversarial Patches : %G eng %U http://hdl.handle.net/21.11116/0000-0008-1662-1 %R 10.1007/978-3-030-68238-5_32 %D 2021 %B 16th European Conference on Computer Vision %Z date of event: 2020-08-23 - 2020-08-28 %C Glasgow, UK %B Computer Vision -- ECCV Workshops 2020 %E Bartoli, Adrian; Fusiello, Andrea %P 429 - 448 %I Springer %@ 978-3-030-68237-8 %B Lecture Notes in Computer Science %N 12539