Toward Practical Adversarial Attacks on Face Verification Systems
| dc.contributor.author | Kakizaki, Kazuya | |
| dc.contributor.author | Miyagawa, Taiki | |
| dc.contributor.author | Singh, Inderjeet | |
| dc.contributor.author | Sakuma, Jun | |
| dc.contributor.editor | Brömme, Arslan | |
| dc.contributor.editor | Busch, Christoph | |
| dc.contributor.editor | Damer, Naser | |
| dc.contributor.editor | Dantcheva, Antitza | |
| dc.contributor.editor | Gomez-Barrero, Marta | |
| dc.contributor.editor | Raja, Kiran | |
| dc.contributor.editor | Rathgeb, Christian | |
| dc.contributor.editor | Sequeira, Ana | |
| dc.contributor.editor | Uhl, Andreas | |
| dc.date.accessioned | 2021-10-04T08:43:43Z | |
| dc.date.available | 2021-10-04T08:43:43Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | DNN-based face verification systems are vulnerable to adversarial examples. The previous paper's evaluation protocol (scenario), which we called the probe-dependent attack scenario, was unrealistic. We define a more practical attack scenario, the probe-agnostic attack. We empirically show that these attacks are more challenging than probe-dependent ones. We propose a simple and effective method, PAMTAM, to improve the attack success rate for probe-agnostic attacks. We show that PAMTAM successfully improves the attack success rate in a wide variety of experimental settings. | en |
| dc.identifier.isbn | 978-3-88579-709-8 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/37446 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-315 | |
| dc.subject | Adversarial example | |
| dc.subject | Face verification | |
| dc.subject | Security | |
| dc.title | Toward Practical Adversarial Attacks on Face Verification Systems | en |
| dc.type | Text/Conference Paper | |
| gi.citation.endPage | 124 | |
| gi.citation.publisherPlace | Bonn | |
| gi.citation.startPage | 113 | |
| gi.conference.date | 15.-17. September 2021 | |
| gi.conference.location | International Digital Conference | |
| gi.conference.sessiontitle | Regular Research Papers |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- biosig2021_proceedings_12.pdf
- Größe:
- 422.71 KB
- Format:
- Adobe Portable Document Format