Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193190996> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3193190996 abstract "Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are susceptible to adversarial examples; adversarial examples are well-crafted malicious inputs to the neural network (NN) with the objective to cause erroneous outputs. In this paper, we extend this to regression problems and show that adversarial attacks can break DL-based power allocation in the downlink of a massive multiple-input-multiple-output (maMIMO) network. Specifically, we extend the fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent adversarial attacks in the context of power allocation in a maMIMO system. We benchmark the performance of these attacks and show that with a small perturbation in the input of the NN, the white-box attacks can result in infeasible solutions up to 86%. Furthermore, we investigate the performance of black-box attacks. All the evaluations conducted in this work are based on an open dataset and NN models, which are publicly available." @default.
- W3193190996 created "2021-08-16" @default.
- W3193190996 creator A5004153335 @default.
- W3193190996 creator A5043552696 @default.
- W3193190996 creator A5074129474 @default.
- W3193190996 date "2021-06-01" @default.
- W3193190996 modified "2023-09-26" @default.
- W3193190996 title "Adversarial Attacks on Deep Learning Based Power Allocation in a Massive MIMO Network" @default.
- W3193190996 cites W2076063813 @default.
- W3193190996 cites W2332630870 @default.
- W3193190996 cites W2736402963 @default.
- W3193190996 cites W2774644650 @default.
- W3193190996 cites W2888024549 @default.
- W3193190996 cites W2917485473 @default.
- W3193190996 cites W2945528624 @default.
- W3193190996 cites W2963101290 @default.
- W3193190996 cites W2963178695 @default.
- W3193190996 cites W2964277700 @default.
- W3193190996 cites W2968867107 @default.
- W3193190996 cites W2983729222 @default.
- W3193190996 cites W2995240473 @default.
- W3193190996 cites W3039795369 @default.
- W3193190996 cites W3042934865 @default.
- W3193190996 cites W3087940812 @default.
- W3193190996 doi "https://doi.org/10.1109/icc42927.2021.9500424" @default.
- W3193190996 hasPublicationYear "2021" @default.
- W3193190996 type Work @default.
- W3193190996 sameAs 3193190996 @default.
- W3193190996 citedByCount "14" @default.
- W3193190996 countsByYear W31931909962021 @default.
- W3193190996 countsByYear W31931909962022 @default.
- W3193190996 countsByYear W31931909962023 @default.
- W3193190996 crossrefType "proceedings-article" @default.
- W3193190996 hasAuthorship W3193190996A5004153335 @default.
- W3193190996 hasAuthorship W3193190996A5043552696 @default.
- W3193190996 hasAuthorship W3193190996A5074129474 @default.
- W3193190996 hasBestOaLocation W31931909962 @default.
- W3193190996 hasConcept C108037233 @default.
- W3193190996 hasConcept C108583219 @default.
- W3193190996 hasConcept C119857082 @default.
- W3193190996 hasConcept C127162648 @default.
- W3193190996 hasConcept C13280743 @default.
- W3193190996 hasConcept C138660444 @default.
- W3193190996 hasConcept C151730666 @default.
- W3193190996 hasConcept C153258448 @default.
- W3193190996 hasConcept C154945302 @default.
- W3193190996 hasConcept C185798385 @default.
- W3193190996 hasConcept C205649164 @default.
- W3193190996 hasConcept C207987634 @default.
- W3193190996 hasConcept C2779343474 @default.
- W3193190996 hasConcept C2984842247 @default.
- W3193190996 hasConcept C37736160 @default.
- W3193190996 hasConcept C41008148 @default.
- W3193190996 hasConcept C50644808 @default.
- W3193190996 hasConcept C555944384 @default.
- W3193190996 hasConcept C76155785 @default.
- W3193190996 hasConcept C86803240 @default.
- W3193190996 hasConcept C94966114 @default.
- W3193190996 hasConceptScore W3193190996C108037233 @default.
- W3193190996 hasConceptScore W3193190996C108583219 @default.
- W3193190996 hasConceptScore W3193190996C119857082 @default.
- W3193190996 hasConceptScore W3193190996C127162648 @default.
- W3193190996 hasConceptScore W3193190996C13280743 @default.
- W3193190996 hasConceptScore W3193190996C138660444 @default.
- W3193190996 hasConceptScore W3193190996C151730666 @default.
- W3193190996 hasConceptScore W3193190996C153258448 @default.
- W3193190996 hasConceptScore W3193190996C154945302 @default.
- W3193190996 hasConceptScore W3193190996C185798385 @default.
- W3193190996 hasConceptScore W3193190996C205649164 @default.
- W3193190996 hasConceptScore W3193190996C207987634 @default.
- W3193190996 hasConceptScore W3193190996C2779343474 @default.
- W3193190996 hasConceptScore W3193190996C2984842247 @default.
- W3193190996 hasConceptScore W3193190996C37736160 @default.
- W3193190996 hasConceptScore W3193190996C41008148 @default.
- W3193190996 hasConceptScore W3193190996C50644808 @default.
- W3193190996 hasConceptScore W3193190996C555944384 @default.
- W3193190996 hasConceptScore W3193190996C76155785 @default.
- W3193190996 hasConceptScore W3193190996C86803240 @default.
- W3193190996 hasConceptScore W3193190996C94966114 @default.
- W3193190996 hasLocation W31931909961 @default.
- W3193190996 hasLocation W31931909962 @default.
- W3193190996 hasOpenAccess W3193190996 @default.
- W3193190996 hasPrimaryLocation W31931909961 @default.
- W3193190996 hasRelatedWork W2180612164 @default.
- W3193190996 hasRelatedWork W2610321374 @default.
- W3193190996 hasRelatedWork W2949152835 @default.
- W3193190996 hasRelatedWork W2952919291 @default.
- W3193190996 hasRelatedWork W3193857078 @default.
- W3193190996 hasRelatedWork W4213432687 @default.
- W3193190996 hasRelatedWork W4225493432 @default.
- W3193190996 hasRelatedWork W4293054861 @default.
- W3193190996 hasRelatedWork W4298388782 @default.
- W3193190996 hasRelatedWork W4300837091 @default.
- W3193190996 isParatext "false" @default.
- W3193190996 isRetracted "false" @default.
- W3193190996 magId "3193190996" @default.
- W3193190996 workType "article" @default.