Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384389992> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4384389992 abstract "In this paper, we present a novel Single-class target-specific Adversarial attack called SingleADV. The goal of SingleADV is to generate a universal perturbation that deceives the target model into confusing a specific category of objects with a target category while ensuring highly relevant and accurate interpretations. The universal perturbation is stochastically and iteratively optimized by minimizing the adversarial loss that is designed to consider both the classifier and interpreter costs in targeted and non-targeted categories. In this optimization framework, ruled by the first- and second-moment estimations, the desired loss surface promotes high confidence and interpretation score of adversarial samples. By avoiding unintended misclassification of samples from other categories, SingleADV enables more effective targeted attacks on interpretable deep learning systems in both white-box and black-box scenarios. To evaluate the effectiveness of SingleADV, we conduct experiments using four different model architectures (ResNet-50, VGG-16, DenseNet-169, and Inception-V3) coupled with three interpretation models (CAM, Grad, and MASK). Through extensive empirical evaluation, we demonstrate that SingleADV effectively deceives the target deep learning models and their associated interpreters under various conditions and settings. Our experimental results show that the performance of SingleADV is effective, with an average fooling ratio of 0.74 and an adversarial confidence level of 0.78 in generating deceptive adversarial samples. Furthermore, we discuss several countermeasures against SingleADV, including a transfer-based learning approach and existing preprocessing defenses." @default.
- W4384389992 created "2023-07-15" @default.
- W4384389992 creator A5016563574 @default.
- W4384389992 creator A5023828527 @default.
- W4384389992 creator A5042456819 @default.
- W4384389992 creator A5069182104 @default.
- W4384389992 creator A5074177185 @default.
- W4384389992 date "2023-07-12" @default.
- W4384389992 modified "2023-09-25" @default.
- W4384389992 title "Single-Class Target-Specific Attack against Interpretable Deep Learning Systems" @default.
- W4384389992 doi "https://doi.org/10.48550/arxiv.2307.06484" @default.
- W4384389992 hasPublicationYear "2023" @default.
- W4384389992 type Work @default.
- W4384389992 citedByCount "0" @default.
- W4384389992 crossrefType "posted-content" @default.
- W4384389992 hasAuthorship W4384389992A5016563574 @default.
- W4384389992 hasAuthorship W4384389992A5023828527 @default.
- W4384389992 hasAuthorship W4384389992A5042456819 @default.
- W4384389992 hasAuthorship W4384389992A5069182104 @default.
- W4384389992 hasAuthorship W4384389992A5074177185 @default.
- W4384389992 hasBestOaLocation W43843899921 @default.
- W4384389992 hasConcept C108583219 @default.
- W4384389992 hasConcept C119857082 @default.
- W4384389992 hasConcept C154945302 @default.
- W4384389992 hasConcept C34736171 @default.
- W4384389992 hasConcept C37736160 @default.
- W4384389992 hasConcept C41008148 @default.
- W4384389992 hasConcept C95623464 @default.
- W4384389992 hasConceptScore W4384389992C108583219 @default.
- W4384389992 hasConceptScore W4384389992C119857082 @default.
- W4384389992 hasConceptScore W4384389992C154945302 @default.
- W4384389992 hasConceptScore W4384389992C34736171 @default.
- W4384389992 hasConceptScore W4384389992C37736160 @default.
- W4384389992 hasConceptScore W4384389992C41008148 @default.
- W4384389992 hasConceptScore W4384389992C95623464 @default.
- W4384389992 hasLocation W43843899921 @default.
- W4384389992 hasOpenAccess W4384389992 @default.
- W4384389992 hasPrimaryLocation W43843899921 @default.
- W4384389992 hasRelatedWork W3158264953 @default.
- W4384389992 hasRelatedWork W4223943233 @default.
- W4384389992 hasRelatedWork W4309045103 @default.
- W4384389992 hasRelatedWork W4312200629 @default.
- W4384389992 hasRelatedWork W4313289316 @default.
- W4384389992 hasRelatedWork W4360585206 @default.
- W4384389992 hasRelatedWork W4364306694 @default.
- W4384389992 hasRelatedWork W4379255972 @default.
- W4384389992 hasRelatedWork W4380086463 @default.
- W4384389992 hasRelatedWork W4383955378 @default.
- W4384389992 isParatext "false" @default.
- W4384389992 isRetracted "false" @default.
- W4384389992 workType "article" @default.