Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384518514> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4384518514 abstract "The boom in deep learning has gained amazing progress in the synthetic aperture radar automatic target recognition (SAR ATR) in recent years. There are strong expectations on the reliability and safety of SAR ATR to avoid security accidents due to applications with high security risks. Unfortunately, it has been demonstrated that deep neural networks are inclined to be highly susceptible to adversarial examples finely crafted by the adversary, which can cause models to deliver an inaccurate prediction with high confidence. Since the adversary's access to and ability to learn about the target SAR systems and classifiers is severely constrained in real-world scenarios. For the SAR ATR task, this necessitates that the adversarial examples produced be highly transferable across the key deep neural network (DNN) classifiers. Additionally, SAR images' redundant speckle noise displays non-robustness and is challenging to generalize across various models. To this end, we in this paper propose an effective untargeted black-box attack algorithm called Positive Weighed Feature Attack (PFWA) for SAR target recognition and introduce novel positive weighted features associated with the region of interest of the model's decision. The primary goal of PWFA is to carry out adversarial attacks by altering the primary motivator for the victim model's choices. The proposed PWFA could produce adversarial examples that are more transferable between various models in this way. Furthermore, we present a random masking approach for reducing the influence of speckle noises. Experiments conducted on the MSTAR dataset prove that the proposed PWFA method is indeed capable of creating adversarial samples that achieve superior performance in terms of transferability." @default.
- W4384518514 created "2023-07-18" @default.
- W4384518514 creator A5009756467 @default.
- W4384518514 creator A5035554947 @default.
- W4384518514 creator A5037230542 @default.
- W4384518514 creator A5049692788 @default.
- W4384518514 date "2023-05-26" @default.
- W4384518514 modified "2023-09-23" @default.
- W4384518514 title "Positive Weighted Feature Attack: Toward Transferable Adversarial Attack to SAR Target Recognition" @default.
- W4384518514 cites W2111847198 @default.
- W4384518514 cites W2138287042 @default.
- W4384518514 cites W2150486153 @default.
- W4384518514 cites W2194775991 @default.
- W4384518514 cites W2292481059 @default.
- W4384518514 cites W2773828237 @default.
- W4384518514 cites W2774644650 @default.
- W4384518514 cites W2896078964 @default.
- W4384518514 cites W2962858109 @default.
- W4384518514 cites W2963446712 @default.
- W4384518514 cites W2963542245 @default.
- W4384518514 cites W2963857521 @default.
- W4384518514 cites W2999606423 @default.
- W4384518514 cites W3035579498 @default.
- W4384518514 cites W3211999566 @default.
- W4384518514 cites W4285295676 @default.
- W4384518514 doi "https://doi.org/10.1109/icetci57876.2023.10176719" @default.
- W4384518514 hasPublicationYear "2023" @default.
- W4384518514 type Work @default.
- W4384518514 citedByCount "0" @default.
- W4384518514 crossrefType "proceedings-article" @default.
- W4384518514 hasAuthorship W4384518514A5009756467 @default.
- W4384518514 hasAuthorship W4384518514A5035554947 @default.
- W4384518514 hasAuthorship W4384518514A5037230542 @default.
- W4384518514 hasAuthorship W4384518514A5049692788 @default.
- W4384518514 hasConcept C104317684 @default.
- W4384518514 hasConcept C108583219 @default.
- W4384518514 hasConcept C117623542 @default.
- W4384518514 hasConcept C119857082 @default.
- W4384518514 hasConcept C138885662 @default.
- W4384518514 hasConcept C140547941 @default.
- W4384518514 hasConcept C153180895 @default.
- W4384518514 hasConcept C154945302 @default.
- W4384518514 hasConcept C185592680 @default.
- W4384518514 hasConcept C26517878 @default.
- W4384518514 hasConcept C2776401178 @default.
- W4384518514 hasConcept C2984842247 @default.
- W4384518514 hasConcept C37736160 @default.
- W4384518514 hasConcept C38652104 @default.
- W4384518514 hasConcept C41008148 @default.
- W4384518514 hasConcept C41065033 @default.
- W4384518514 hasConcept C41895202 @default.
- W4384518514 hasConcept C49937458 @default.
- W4384518514 hasConcept C50644808 @default.
- W4384518514 hasConcept C55493867 @default.
- W4384518514 hasConcept C63479239 @default.
- W4384518514 hasConcept C87360688 @default.
- W4384518514 hasConceptScore W4384518514C104317684 @default.
- W4384518514 hasConceptScore W4384518514C108583219 @default.
- W4384518514 hasConceptScore W4384518514C117623542 @default.
- W4384518514 hasConceptScore W4384518514C119857082 @default.
- W4384518514 hasConceptScore W4384518514C138885662 @default.
- W4384518514 hasConceptScore W4384518514C140547941 @default.
- W4384518514 hasConceptScore W4384518514C153180895 @default.
- W4384518514 hasConceptScore W4384518514C154945302 @default.
- W4384518514 hasConceptScore W4384518514C185592680 @default.
- W4384518514 hasConceptScore W4384518514C26517878 @default.
- W4384518514 hasConceptScore W4384518514C2776401178 @default.
- W4384518514 hasConceptScore W4384518514C2984842247 @default.
- W4384518514 hasConceptScore W4384518514C37736160 @default.
- W4384518514 hasConceptScore W4384518514C38652104 @default.
- W4384518514 hasConceptScore W4384518514C41008148 @default.
- W4384518514 hasConceptScore W4384518514C41065033 @default.
- W4384518514 hasConceptScore W4384518514C41895202 @default.
- W4384518514 hasConceptScore W4384518514C49937458 @default.
- W4384518514 hasConceptScore W4384518514C50644808 @default.
- W4384518514 hasConceptScore W4384518514C55493867 @default.
- W4384518514 hasConceptScore W4384518514C63479239 @default.
- W4384518514 hasConceptScore W4384518514C87360688 @default.
- W4384518514 hasLocation W43845185141 @default.
- W4384518514 hasOpenAccess W4384518514 @default.
- W4384518514 hasPrimaryLocation W43845185141 @default.
- W4384518514 hasRelatedWork W2543161807 @default.
- W4384518514 hasRelatedWork W2640329709 @default.
- W4384518514 hasRelatedWork W2952919291 @default.
- W4384518514 hasRelatedWork W2973417394 @default.
- W4384518514 hasRelatedWork W3175269475 @default.
- W4384518514 hasRelatedWork W3193857078 @default.
- W4384518514 hasRelatedWork W3208304128 @default.
- W4384518514 hasRelatedWork W4293846201 @default.
- W4384518514 hasRelatedWork W4379255972 @default.
- W4384518514 hasRelatedWork W4383955378 @default.
- W4384518514 isParatext "false" @default.
- W4384518514 isRetracted "false" @default.
- W4384518514 workType "article" @default.