File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2019.00526
- Scopus: eid_2-s2.0-85081891119
- WOS: WOS:000548549200015
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Once a man: Towards multi-target attack via learning multi-target adversarial network once
Title | Once a man: Towards multi-target attack via learning multi-target adversarial network once |
---|---|
Authors | |
Issue Date | 2019 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 |
Citation | Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October - 2 November 2019, p. 5157-5166 How to Cite? |
Abstract | Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making them not applicable to real classification systems that often have hundreds/thousands of categories. In this paper, we propose the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model. By incorporating the specified category information into the intermediate features, it can attack any category of the target classification model during runtime. Experiments show that the proposed MAN can produce stronger attack results and also have better transferability than previous state-of-the-art methods in both multi-target attack task and single-target attack task. We further use the adversarial samples generated by our MAN to improve the robustness of the classification model. It can also achieve better classification accuracy than other methods when attacked by various methods. |
Persistent Identifier | http://hdl.handle.net/10722/284156 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, J | - |
dc.contributor.author | Dong, X | - |
dc.contributor.author | Zhang, R | - |
dc.contributor.author | Chen, D | - |
dc.contributor.author | Zhang, W | - |
dc.contributor.author | Yu, N | - |
dc.contributor.author | Luo, P | - |
dc.contributor.author | Wang, X | - |
dc.date.accessioned | 2020-07-20T05:56:32Z | - |
dc.date.available | 2020-07-20T05:56:32Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October - 2 November 2019, p. 5157-5166 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/284156 | - |
dc.description.abstract | Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making them not applicable to real classification systems that often have hundreds/thousands of categories. In this paper, we propose the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model. By incorporating the specified category information into the intermediate features, it can attack any category of the target classification model during runtime. Experiments show that the proposed MAN can produce stronger attack results and also have better transferability than previous state-of-the-art methods in both multi-target attack task and single-target attack task. We further use the adversarial samples generated by our MAN to improve the robustness of the classification model. It can also achieve better classification accuracy than other methods when attacked by various methods. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 | - |
dc.relation.ispartof | IEEE International Conference on Computer Vision (ICCV) Proceedings | - |
dc.rights | IEEE International Conference on Computer Vision (ICCV) Proceedings. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.title | Once a man: Towards multi-target attack via learning multi-target adversarial network once | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.doi | 10.1109/ICCV.2019.00526 | - |
dc.identifier.scopus | eid_2-s2.0-85081891119 | - |
dc.identifier.hkuros | 311016 | - |
dc.identifier.spage | 5157 | - |
dc.identifier.epage | 5166 | - |
dc.identifier.isi | WOS:000548549200015 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1550-5499 | - |