FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904169782> ?p ?o ?g. }

• W2904169782 endingPage "1484" @default.
• W2904169782 startingPage "1473" @default.
• W2904169782 abstract "Due to its strong representation learning ability and its facilitation of joint learning for representation and hash codes, deep learning-to-hash has achieved promising results and is becoming increasingly popular for the large-scale approximate nearest neighbor search. However, recent studies highlight the vulnerability of deep image classifiers to adversarial examples; this also introduces profound security concerns for deep retrieval systems. Accordingly, in order to study the robustness of modern deep hashing models to adversarial perturbations, we propose hash adversary generation (HAG), a novel method of crafting adversarial examples for Hamming space search. The main goal of HAG is to generate imperceptibly perturbed examples as queries, whose nearest neighbors from a targeted hashing model are semantically irrelevant to the original queries. Extensive experiments prove that HAG can successfully craft adversarial examples with small perturbations to mislead targeted hashing models. The transferability of these perturbations under a variety of settings is also verified. Moreover, by combining heterogeneous perturbations, we further provide a simple yet effective method of constructing adversarial examples for black-box attacks." @default.
• W2904169782 created "2018-12-22" @default.
• W2904169782 creator A5015874725 @default.
• W2904169782 creator A5057526429 @default.
• W2904169782 creator A5065250332 @default.
• W2904169782 creator A5074103823 @default.
• W2904169782 date "2020-04-01" @default.
• W2904169782 modified "2023-10-17" @default.
• W2904169782 title "Adversarial Examples for Hamming Space Search" @default.
• W2904169782 cites W1913628733 @default.
• W2904169782 cites W1939575207 @default.
• W2904169782 cites W1947372417 @default.
• W2904169782 cites W1956333070 @default.
• W2904169782 cites W1974647172 @default.
• W2904169782 cites W1990537115 @default.
• W2904169782 cites W2017615984 @default.
• W2904169782 cites W2058116810 @default.
• W2904169782 cites W2142040641 @default.
• W2904169782 cites W2145065594 @default.
• W2904169782 cites W2153273131 @default.
• W2904169782 cites W2295151578 @default.
• W2904169782 cites W2412709527 @default.
• W2904169782 cites W2461086877 @default.
• W2904169782 cites W2464915613 @default.
• W2904169782 cites W2497571620 @default.
• W2904169782 cites W2564853008 @default.
• W2904169782 cites W2594227027 @default.
• W2904169782 cites W2598003564 @default.
• W2904169782 cites W2604505099 @default.
• W2904169782 cites W2725751619 @default.
• W2904169782 cites W2733548594 @default.
• W2904169782 cites W2739103128 @default.
• W2904169782 cites W2749777401 @default.
• W2904169782 cites W2781787169 @default.
• W2904169782 cites W2787487383 @default.
• W2904169782 cites W2791083848 @default.
• W2904169782 cites W2795431490 @default.
• W2904169782 cites W2795832645 @default.
• W2904169782 cites W2798834175 @default.
• W2904169782 cites W2807944281 @default.
• W2904169782 cites W2808282156 @default.
• W2904169782 cites W2809771837 @default.
• W2904169782 cites W2913932916 @default.
• W2904169782 cites W2963187862 @default.
• W2904169782 cites W2963564844 @default.
• W2904169782 cites W2964082701 @default.
• W2904169782 cites W2964280870 @default.
• W2904169782 cites W2964301649 @default.
• W2904169782 cites W3103722964 @default.
• W2904169782 cites W4240108565 @default.
• W2904169782 doi "https://doi.org/10.1109/tcyb.2018.2882908" @default.
• W2904169782 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30561358" @default.
• W2904169782 hasPublicationYear "2020" @default.
• W2904169782 type Work @default.
• W2904169782 sameAs 2904169782 @default.
• W2904169782 citedByCount "59" @default.
• W2904169782 countsByYear W29041697822019 @default.
• W2904169782 countsByYear W29041697822020 @default.
• W2904169782 countsByYear W29041697822021 @default.
• W2904169782 countsByYear W29041697822022 @default.
• W2904169782 countsByYear W29041697822023 @default.
• W2904169782 crossrefType "journal-article" @default.
• W2904169782 hasAuthorship W2904169782A5015874725 @default.
• W2904169782 hasAuthorship W2904169782A5057526429 @default.
• W2904169782 hasAuthorship W2904169782A5065250332 @default.
• W2904169782 hasAuthorship W2904169782A5074103823 @default.
• W2904169782 hasConcept C104317684 @default.
• W2904169782 hasConcept C108583219 @default.
• W2904169782 hasConcept C11413529 @default.
• W2904169782 hasConcept C119857082 @default.
• W2904169782 hasConcept C133667856 @default.
• W2904169782 hasConcept C138111711 @default.
• W2904169782 hasConcept C154945302 @default.
• W2904169782 hasConcept C157125643 @default.
• W2904169782 hasConcept C17744445 @default.
• W2904169782 hasConcept C185592680 @default.
• W2904169782 hasConcept C193319292 @default.
• W2904169782 hasConcept C199539241 @default.
• W2904169782 hasConcept C2776359362 @default.
• W2904169782 hasConcept C2779494224 @default.
• W2904169782 hasConcept C37736160 @default.
• W2904169782 hasConcept C38652104 @default.
• W2904169782 hasConcept C41008148 @default.
• W2904169782 hasConcept C55493867 @default.
• W2904169782 hasConcept C57273362 @default.
• W2904169782 hasConcept C63479239 @default.
• W2904169782 hasConcept C67388219 @default.
• W2904169782 hasConcept C73150493 @default.
• W2904169782 hasConcept C80444323 @default.
• W2904169782 hasConcept C94625758 @default.
• W2904169782 hasConcept C99138194 @default.
• W2904169782 hasConceptScore W2904169782C104317684 @default.
• W2904169782 hasConceptScore W2904169782C108583219 @default.
• W2904169782 hasConceptScore W2904169782C11413529 @default.
• W2904169782 hasConceptScore W2904169782C119857082 @default.
• W2904169782 hasConceptScore W2904169782C133667856 @default.
• W2904169782 hasConceptScore W2904169782C138111711 @default.
• W2904169782 hasConceptScore W2904169782C154945302 @default.

• next