Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384434564> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4384434564 endingPage "57" @default.
- W4384434564 startingPage "34" @default.
- W4384434564 abstract "Being widely adopted by an increasingly rich array of classification tasks in different industries, image classifiers based on deep neural networks (DNNs) have successfully helped boost business efficiency and reduce costs. To protect the intellectual property (IP) of DNN classifiers, a blind-watermarking-based technique that opens “backdoors” through image steganography has been proposed. However, it is yet to explore whether this approach can effectively protect DNN models under practical settings where malicious attacks may be launched against it. In this paper, we study the feasibility and effectiveness of this previously proposed blind-watermarking-based DNN classifier protection technique from the security perspective (Our code is available at https://github.com/ByGary/Security-of-IP-Protection-Frameworks .). We first show that, IP protection offered by the original algorithm, when trained with $$256,times ,256$$ images, can easily be evaded due to obvious visibility issue. Adapting the original approach by replacing its steganalyzer with watermark extraction algorithm and revising the overall training strategy, we are able to mitigate the visibility issue. Furthermore, we evaluate our improved approaches under three simple yet practical attacks, i.e., evasion attacks, spoofing attacks, and robustness attacks. Our evaluation results reveal that further security enhancements are indispensable for the practical applications of the examined blind-watermarking-based DNN image classifier protection scheme, providing a set of guidelines and precautions to facilitate improved protection of intellectual property of DNN classifiers." @default.
- W4384434564 created "2023-07-16" @default.
- W4384434564 creator A5004233794 @default.
- W4384434564 creator A5027922810 @default.
- W4384434564 creator A5071440390 @default.
- W4384434564 creator A5087166824 @default.
- W4384434564 creator A5012881738 @default.
- W4384434564 date "2023-01-01" @default.
- W4384434564 modified "2023-10-12" @default.
- W4384434564 title "Can Image Watermarking Efficiently Protect Deep-Learning-Based Image Classifiers? – A Preliminary Security Analysis of an IP-Protecting Method" @default.
- W4384434564 cites W2151346626 @default.
- W4384434564 cites W2194775991 @default.
- W4384434564 cites W2322622188 @default.
- W4384434564 cites W2416075718 @default.
- W4384434564 cites W2621048556 @default.
- W4384434564 cites W2806082141 @default.
- W4384434564 cites W2892948265 @default.
- W4384434564 cites W2919023666 @default.
- W4384434564 cites W2963462425 @default.
- W4384434564 cites W2990980946 @default.
- W4384434564 cites W3008519165 @default.
- W4384434564 cites W3009879448 @default.
- W4384434564 cites W3081073185 @default.
- W4384434564 cites W3102111060 @default.
- W4384434564 cites W3122311785 @default.
- W4384434564 cites W3133747496 @default.
- W4384434564 cites W3135872251 @default.
- W4384434564 cites W3156793535 @default.
- W4384434564 cites W3164111940 @default.
- W4384434564 cites W3164581645 @default.
- W4384434564 cites W3164878287 @default.
- W4384434564 cites W3168768313 @default.
- W4384434564 cites W3175133087 @default.
- W4384434564 cites W3179479348 @default.
- W4384434564 cites W3195438473 @default.
- W4384434564 cites W3211456420 @default.
- W4384434564 cites W3216717225 @default.
- W4384434564 cites W4200288056 @default.
- W4384434564 cites W4214543711 @default.
- W4384434564 cites W4308900984 @default.
- W4384434564 doi "https://doi.org/10.1007/978-3-031-36574-4_3" @default.
- W4384434564 hasPublicationYear "2023" @default.
- W4384434564 type Work @default.
- W4384434564 citedByCount "0" @default.
- W4384434564 crossrefType "book-chapter" @default.
- W4384434564 hasAuthorship W4384434564A5004233794 @default.
- W4384434564 hasAuthorship W4384434564A5012881738 @default.
- W4384434564 hasAuthorship W4384434564A5027922810 @default.
- W4384434564 hasAuthorship W4384434564A5071440390 @default.
- W4384434564 hasAuthorship W4384434564A5087166824 @default.
- W4384434564 hasConcept C104317684 @default.
- W4384434564 hasConcept C108583219 @default.
- W4384434564 hasConcept C111919701 @default.
- W4384434564 hasConcept C115961682 @default.
- W4384434564 hasConcept C119857082 @default.
- W4384434564 hasConcept C150817343 @default.
- W4384434564 hasConcept C154945302 @default.
- W4384434564 hasConcept C164112704 @default.
- W4384434564 hasConcept C185592680 @default.
- W4384434564 hasConcept C34974158 @default.
- W4384434564 hasConcept C38652104 @default.
- W4384434564 hasConcept C41008148 @default.
- W4384434564 hasConcept C55493867 @default.
- W4384434564 hasConcept C63479239 @default.
- W4384434564 hasConcept C95623464 @default.
- W4384434564 hasConceptScore W4384434564C104317684 @default.
- W4384434564 hasConceptScore W4384434564C108583219 @default.
- W4384434564 hasConceptScore W4384434564C111919701 @default.
- W4384434564 hasConceptScore W4384434564C115961682 @default.
- W4384434564 hasConceptScore W4384434564C119857082 @default.
- W4384434564 hasConceptScore W4384434564C150817343 @default.
- W4384434564 hasConceptScore W4384434564C154945302 @default.
- W4384434564 hasConceptScore W4384434564C164112704 @default.
- W4384434564 hasConceptScore W4384434564C185592680 @default.
- W4384434564 hasConceptScore W4384434564C34974158 @default.
- W4384434564 hasConceptScore W4384434564C38652104 @default.
- W4384434564 hasConceptScore W4384434564C41008148 @default.
- W4384434564 hasConceptScore W4384434564C55493867 @default.
- W4384434564 hasConceptScore W4384434564C63479239 @default.
- W4384434564 hasConceptScore W4384434564C95623464 @default.
- W4384434564 hasLocation W43844345641 @default.
- W4384434564 hasOpenAccess W4384434564 @default.
- W4384434564 hasPrimaryLocation W43844345641 @default.
- W4384434564 hasRelatedWork W1693642297 @default.
- W4384434564 hasRelatedWork W2042311553 @default.
- W4384434564 hasRelatedWork W2081730827 @default.
- W4384434564 hasRelatedWork W2157294580 @default.
- W4384434564 hasRelatedWork W2340838230 @default.
- W4384434564 hasRelatedWork W2363475415 @default.
- W4384434564 hasRelatedWork W3106527215 @default.
- W4384434564 hasRelatedWork W4224919626 @default.
- W4384434564 hasRelatedWork W4310220500 @default.
- W4384434564 hasRelatedWork W2157307195 @default.
- W4384434564 isParatext "false" @default.
- W4384434564 isRetracted "false" @default.
- W4384434564 workType "book-chapter" @default.