1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPAW/3PK8JAB |
Repository | sid.inpe.br/sibgrapi/2017/09.11.16.27 |
Last Update | 2017:09.11.16.27.29 (UTC) tabacof@gmail.com |
Metadata Repository | sid.inpe.br/sibgrapi/2017/09.11.16.27.29 |
Metadata Last Update | 2022:05.18.22.18.26 (UTC) administrator |
Citation Key | TabacofVall:2017:ExAdIm |
Title | Exploring Adversarial Images in Deep Neural Networks |
Format | On-line |
Year | 2017 |
Access Date | 2024, May 02 |
Number of Files | 1 |
Size | 2484 KiB |
|
2. Context | |
Author | 1 Tabacof, Pedro 2 Valle, Eduardo |
Affiliation | 1 University of Campinas 2 University of Campinas |
Editor | Torchelsen, Rafael Piccin Nascimento, Erickson Rangel do Panozzo, Daniele Liu, Zicheng Farias, Mylène Viera, Thales Sacht, Leonardo Ferreira, Nivan Comba, João Luiz Dihl Hirata, Nina Schiavon Porto, Marcelo Vital, Creto Pagot, Christian Azambuja Petronetto, Fabiano Clua, Esteban Cardeal, Flávio |
e-Mail Address | tabacof@gmail.com |
Conference Name | Conference on Graphics, Patterns and Images, 30 (SIBGRAPI) |
Conference Location | Niterói, RJ, Brazil |
Date | 17-20 Oct. 2017 |
Publisher | Sociedade Brasileira de Computação |
Publisher City | Porto Alegre |
Book Title | Proceedings |
Tertiary Type | Master's or Doctoral Work |
History (UTC) | 2017-09-11 16:27:29 :: tabacof@gmail.com -> administrator :: 2022-05-18 22:18:26 :: administrator -> :: 2017 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Keywords | deep learning neural networks adversarial images |
Abstract | Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pre-trained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using deep classifiers on the ImageNet dataset. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images appear in large regions in the pixel space, and that it is hard to leave those regions by adding noise to the images, even with high intensity. |
Arrangement | urlib.net > SDLA > Fonds > SIBGRAPI 2017 > Exploring Adversarial Images... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPAW/3PK8JAB |
zipped data URL | http://urlib.net/zip/8JMKD3MGPAW/3PK8JAB |
Language | en |
Target File | sibgrapi (1).pdf |
User Group | tabacof@gmail.com |
Visibility | shown |
Update Permission | not transferred |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPAW/3PKCC58 |
Citing Item List | sid.inpe.br/sibgrapi/2017/09.12.13.04 9 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume |
|