CD-UAP: Class Discriminative Universal Adversarial Perturbation

Cited 29 time in webofscience Cited 0 time in scopus
  • Hit : 75
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorZhang, Chaoningko
dc.contributor.authorBenz, Philippko
dc.contributor.authorImtiaz, Toobako
dc.contributor.authorKweon, In-Soko
dc.date.accessioned2021-10-29T01:30:23Z-
dc.date.available2021-10-29T01:30:23Z-
dc.date.created2021-10-19-
dc.date.created2021-10-19-
dc.date.issued2020-02-
dc.identifier.citation34th AAAI Conference on Artificial Intelligence / 32nd Innovative Applications of Artificial Intelligence Conference / 10th AAAI Symposium on Educational Advances in Artificial Intelligence, pp.6754 - 6761-
dc.identifier.issn2159-5399-
dc.identifier.urihttp://hdl.handle.net/10203/288431-
dc.description.abstractA single universal adversarial perturbation (UAP) can be added to all natural images to change most of their predicted class labels. It is of high practical relevance for an attacker to have flexible control over the targeted classes to be attacked, however, the existing UAP method attacks samples from all classes. In this work, we propose a new universal attack method to generate a single perturbation that fools a target network to misclassify only a chosen group of classes, while having limited influence on the remaining classes. Since the proposed attack generates a universal adversarial perturbation that is discriminative to targeted and non-targeted classes, we term it class discriminative universal adversarial perturbation (CD-UAP). We propose one simple yet effective algorithm framework, under which we design and compare various loss function configurations tailored for the class discriminative universal attack. The proposed approach has been evaluated with extensive experiments on various benchmark datasets. Additionally, our proposed approach achieves state-of-the-art performance for the original task of UAP attacking all classes, which demonstrates the effectiveness of our approach.-
dc.languageEnglish-
dc.publisherASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE-
dc.titleCD-UAP: Class Discriminative Universal Adversarial Perturbation-
dc.typeConference-
dc.identifier.wosid000667722806103-
dc.identifier.scopusid2-s2.0-85094678734-
dc.type.rimsCONF-
dc.citation.beginningpage6754-
dc.citation.endingpage6761-
dc.citation.publicationname34th AAAI Conference on Artificial Intelligence / 32nd Innovative Applications of Artificial Intelligence Conference / 10th AAAI Symposium on Educational Advances in Artificial Intelligence-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationNew York, NY-
dc.contributor.localauthorKweon, In-So-
dc.contributor.nonIdAuthorImtiaz, Tooba-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 29 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0