FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386996713> ?p ?o ?g. }

• W4386996713 endingPage "4660" @default.
• W4386996713 startingPage "4660" @default.
• W4386996713 abstract "As a safety-related application, visual systems based on deep neural networks (DNNs) in modern unmanned aerial vehicles (UAVs) show adversarial vulnerability when performing real-time inference. Recently, deep ensembles with various defensive strategies against adversarial samples have drawn much attention due to the increased diversity and reduced variance for their members. Aimed at the recognition task of remote sensing images (RSIs), this paper proposes to use a reactive-proactive ensemble defense framework to solve the security problem. In reactive defense, we fuse scoring functions of several classical detection algorithms with the hidden features and average output confidences from sub-models as a second fusion. In terms of proactive defense, we attempt two strategies, including enhancing the robustness of each sub-model and limiting the transferability among sub-models. In practical applications, the real-time RSIs are first input to the reactive defense part, which can detect and reject the adversarial RSIs. The accepted ones are then passed to robust recognition with a proactive defense. We conduct extensive experiments on three benchmark RSI datasets (i.e., UCM, AID, and FGSC-23). The experimental results show that the deep ensemble method of reactive and proactive defense performs very well in gradient-based attacks. The analysis of the applicable attack scenarios for each proactive ensemble defense is also helpful for this field. We also perform a case study with the whole framework in the black-box scenario, and the highest detection rate reaches 93.25%. Most of the adversarial RSIs can be rejected in advance or correctly recognized by the enhanced deep ensemble. This article is the first one to combine reactive and proactive defenses with a deep ensemble against adversarial attacks in the context of RSI recognition for DNN-based UAVs." @default.
• W4386996713 created "2023-09-25" @default.
• W4386996713 creator A5005681876 @default.
• W4386996713 creator A5026265793 @default.
• W4386996713 creator A5082887216 @default.
• W4386996713 creator A5089424445 @default.
• W4386996713 date "2023-09-22" @default.
• W4386996713 modified "2023-09-30" @default.
• W4386996713 title "Adversarial Robust Aerial Image Recognition Based on Reactive-Proactive Defense Framework with Deep Ensembles" @default.
• W4386996713 cites W1934570606 @default.
• W4386996713 cites W1980038761 @default.
• W4386996713 cites W2115629999 @default.
• W4386996713 cites W2194775991 @default.
• W4386996713 cites W2243397390 @default.
• W4386996713 cites W2774644650 @default.
• W4386996713 cites W2889149612 @default.
• W4386996713 cites W2889621419 @default.
• W4386996713 cites W2962700793 @default.
• W4386996713 cites W2963178695 @default.
• W4386996713 cites W2963229629 @default.
• W4386996713 cites W2963542245 @default.
• W4386996713 cites W2963636205 @default.
• W4386996713 cites W2963857521 @default.
• W4386996713 cites W2964082701 @default.
• W4386996713 cites W2966845869 @default.
• W4386996713 cites W2970602317 @default.
• W4386996713 cites W2984534168 @default.
• W4386996713 cites W2998600476 @default.
• W4386996713 cites W3035182590 @default.
• W4386996713 cites W3035821888 @default.
• W4386996713 cites W3044816028 @default.
• W4386996713 cites W3100144085 @default.
• W4386996713 cites W3105577662 @default.
• W4386996713 cites W3110144845 @default.
• W4386996713 cites W3130510369 @default.
• W4386996713 cites W3149839747 @default.
• W4386996713 cites W3157241031 @default.
• W4386996713 cites W3194110702 @default.
• W4386996713 cites W3196302005 @default.
• W4386996713 cites W3198216469 @default.
• W4386996713 cites W3200113267 @default.
• W4386996713 cites W3208634274 @default.
• W4386996713 cites W3211999566 @default.
• W4386996713 cites W4200231721 @default.
• W4386996713 cites W4205434352 @default.
• W4386996713 cites W4206002950 @default.
• W4386996713 cites W4211068785 @default.
• W4386996713 cites W4221051356 @default.
• W4386996713 cites W4225502793 @default.
• W4386996713 cites W4226239489 @default.
• W4386996713 cites W4288048332 @default.
• W4386996713 cites W4296340043 @default.
• W4386996713 cites W4312318241 @default.
• W4386996713 cites W4372260187 @default.
• W4386996713 cites W4378191955 @default.
• W4386996713 cites W4380142931 @default.
• W4386996713 cites W4385164057 @default.
• W4386996713 cites W4386075665 @default.
• W4386996713 doi "https://doi.org/10.3390/rs15194660" @default.
• W4386996713 hasPublicationYear "2023" @default.
• W4386996713 type Work @default.
• W4386996713 citedByCount "0" @default.
• W4386996713 crossrefType "journal-article" @default.
• W4386996713 hasAuthorship W4386996713A5005681876 @default.
• W4386996713 hasAuthorship W4386996713A5026265793 @default.
• W4386996713 hasAuthorship W4386996713A5082887216 @default.
• W4386996713 hasAuthorship W4386996713A5089424445 @default.
• W4386996713 hasBestOaLocation W43869967131 @default.
• W4386996713 hasConcept C104317684 @default.
• W4386996713 hasConcept C108583219 @default.
• W4386996713 hasConcept C119857082 @default.
• W4386996713 hasConcept C127413603 @default.
• W4386996713 hasConcept C13280743 @default.
• W4386996713 hasConcept C140331021 @default.
• W4386996713 hasConcept C154945302 @default.
• W4386996713 hasConcept C185592680 @default.
• W4386996713 hasConcept C185798385 @default.
• W4386996713 hasConcept C188198153 @default.
• W4386996713 hasConcept C205649164 @default.
• W4386996713 hasConcept C2776214188 @default.
• W4386996713 hasConcept C2984842247 @default.
• W4386996713 hasConcept C37736160 @default.
• W4386996713 hasConcept C41008148 @default.
• W4386996713 hasConcept C55493867 @default.
• W4386996713 hasConcept C61272859 @default.
• W4386996713 hasConcept C63479239 @default.
• W4386996713 hasConcept C78519656 @default.
• W4386996713 hasConceptScore W4386996713C104317684 @default.
• W4386996713 hasConceptScore W4386996713C108583219 @default.
• W4386996713 hasConceptScore W4386996713C119857082 @default.
• W4386996713 hasConceptScore W4386996713C127413603 @default.
• W4386996713 hasConceptScore W4386996713C13280743 @default.
• W4386996713 hasConceptScore W4386996713C140331021 @default.
• W4386996713 hasConceptScore W4386996713C154945302 @default.
• W4386996713 hasConceptScore W4386996713C185592680 @default.
• W4386996713 hasConceptScore W4386996713C185798385 @default.
• W4386996713 hasConceptScore W4386996713C188198153 @default.
• W4386996713 hasConceptScore W4386996713C205649164 @default.

• next