Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324291272> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4324291272 endingPage "12950" @default.
- W4324291272 startingPage "12938" @default.
- W4324291272 abstract "In spite of unique advantages like higher recognition accuracy and better generalization capability, automatic modulation classification (AMC)-oriented deep neural networks (ADNNs) are still vulnerable to adversarial examples (AEs). Recent results revealed that an attacker can easily fool ADNNs through adding a small and imperceptible perturbation to the original signal. Among different AE generation methods, universal adversarial perturbation (UAP) has unique characteristics, including input agnostic and shift invariance. However, applying UAP directly to RF signals faces three main challenges, i.e., perturbation neutralization, high perceptibility, and dependency of original signals. In this backdrop, a novel UAP under frequency and data constraints (UAP-FD) attack is put forward for solving these problems in this article. First, an individual perturbation is filtered based on the representation visualization algorithm to counter the neutralization problem in perturbation integration. Second, the high-frequency components in the integrated UAP is eliminated through signal decomposition and reconstruction for promoting the imperceptibility. Third, a proxy signal generation method is proposed to help UAP-FD adapt to data-free black-box settings. A series of experiments is conducted to evaluate the aggressiveness and imperceptibility of UAP-FD attack in different settings on a public data set. Results show that, compared with the existing proposal, UAP-FD has a 40% higher fooling rate, and it can reduce the accuracy of the ADNN model from 83% to 9% while maintaining a good imperceptibility and shift-invariance property. In addition, UAP-FD is applied to real-world captured signals over the transmission channel; and it can reduce the model accuracy from 98.3% to 12.5%." @default.
- W4324291272 created "2023-03-16" @default.
- W4324291272 creator A5021951002 @default.
- W4324291272 creator A5029634246 @default.
- W4324291272 creator A5038562656 @default.
- W4324291272 creator A5059879436 @default.
- W4324291272 creator A5063881675 @default.
- W4324291272 date "2023-07-15" @default.
- W4324291272 modified "2023-09-30" @default.
- W4324291272 title "Universal Attack Against Automatic Modulation Classification DNNs Under Frequency and Data Constraints" @default.
- W4324291272 cites W2125056386 @default.
- W4324291272 cites W2180612164 @default.
- W4324291272 cites W2243397390 @default.
- W4324291272 cites W2272847350 @default.
- W4324291272 cites W2543927648 @default.
- W4324291272 cites W2603396821 @default.
- W4324291272 cites W2612824601 @default.
- W4324291272 cites W2746600820 @default.
- W4324291272 cites W2773170971 @default.
- W4324291272 cites W2888024549 @default.
- W4324291272 cites W2892154397 @default.
- W4324291272 cites W2917677817 @default.
- W4324291272 cites W2945528624 @default.
- W4324291272 cites W2946313841 @default.
- W4324291272 cites W2962858109 @default.
- W4324291272 cites W2963448658 @default.
- W4324291272 cites W2963542245 @default.
- W4324291272 cites W2963857521 @default.
- W4324291272 cites W2986517689 @default.
- W4324291272 cites W2999338743 @default.
- W4324291272 cites W3003438155 @default.
- W4324291272 cites W3015061735 @default.
- W4324291272 cites W3023683268 @default.
- W4324291272 cites W3023850691 @default.
- W4324291272 cites W3045729505 @default.
- W4324291272 cites W3047492485 @default.
- W4324291272 cites W3048657120 @default.
- W4324291272 cites W3098755434 @default.
- W4324291272 cites W3133729763 @default.
- W4324291272 cites W3191186757 @default.
- W4324291272 cites W3205236965 @default.
- W4324291272 cites W3205971195 @default.
- W4324291272 cites W3213282580 @default.
- W4324291272 cites W4224920283 @default.
- W4324291272 cites W4226117432 @default.
- W4324291272 cites W4226314137 @default.
- W4324291272 cites W4295308574 @default.
- W4324291272 cites W4306893691 @default.
- W4324291272 doi "https://doi.org/10.1109/jiot.2023.3254648" @default.
- W4324291272 hasPublicationYear "2023" @default.
- W4324291272 type Work @default.
- W4324291272 citedByCount "1" @default.
- W4324291272 countsByYear W43242912722023 @default.
- W4324291272 crossrefType "journal-article" @default.
- W4324291272 hasAuthorship W4324291272A5021951002 @default.
- W4324291272 hasAuthorship W4324291272A5029634246 @default.
- W4324291272 hasAuthorship W4324291272A5038562656 @default.
- W4324291272 hasAuthorship W4324291272A5059879436 @default.
- W4324291272 hasAuthorship W4324291272A5063881675 @default.
- W4324291272 hasConcept C11413529 @default.
- W4324291272 hasConcept C121332964 @default.
- W4324291272 hasConcept C124101348 @default.
- W4324291272 hasConcept C153180895 @default.
- W4324291272 hasConcept C154945302 @default.
- W4324291272 hasConcept C177918212 @default.
- W4324291272 hasConcept C41008148 @default.
- W4324291272 hasConcept C62520636 @default.
- W4324291272 hasConceptScore W4324291272C11413529 @default.
- W4324291272 hasConceptScore W4324291272C121332964 @default.
- W4324291272 hasConceptScore W4324291272C124101348 @default.
- W4324291272 hasConceptScore W4324291272C153180895 @default.
- W4324291272 hasConceptScore W4324291272C154945302 @default.
- W4324291272 hasConceptScore W4324291272C177918212 @default.
- W4324291272 hasConceptScore W4324291272C41008148 @default.
- W4324291272 hasConceptScore W4324291272C62520636 @default.
- W4324291272 hasFunder F4320321001 @default.
- W4324291272 hasIssue "14" @default.
- W4324291272 hasLocation W43242912721 @default.
- W4324291272 hasOpenAccess W4324291272 @default.
- W4324291272 hasPrimaryLocation W43242912721 @default.
- W4324291272 hasRelatedWork W2033914206 @default.
- W4324291272 hasRelatedWork W2042327336 @default.
- W4324291272 hasRelatedWork W2046077695 @default.
- W4324291272 hasRelatedWork W2146076056 @default.
- W4324291272 hasRelatedWork W2163831990 @default.
- W4324291272 hasRelatedWork W2378160586 @default.
- W4324291272 hasRelatedWork W2996038082 @default.
- W4324291272 hasRelatedWork W3003836766 @default.
- W4324291272 hasRelatedWork W3047965787 @default.
- W4324291272 hasRelatedWork W3184582087 @default.
- W4324291272 hasVolume "10" @default.
- W4324291272 isParatext "false" @default.
- W4324291272 isRetracted "false" @default.
- W4324291272 workType "article" @default.