Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132130305> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3132130305 abstract "Although image translation algorithms such as StarGAN, STGAN, StarGAN-v2, etc. based on the generative adversarial networks, bring enormous convenience to people's work and life, they also have greater security risks in terms of privacy and security ethics. We tackle this problem of generating adversarial attacks against image translation models, which disrupt the resulting output image. The existing adversarial technology can only generate adversarial samples for a single image translation model, but in actual applications, it is unknown to the user which model an attacker will use. The paper draws on the idea of multi-task learning and proposes a multi-objective adversarial sample generation algorithm to generate images that can simultaneously defend against tampering with multiple state- of-the-art image translation models. The simulation result shows that compared with the original images, adversarial images have no heavy visual distortion with PSNR of 27.17dB and SSIM of 0.70 which means that normal usages of images, such as showing something interesting, amazing, funny, cool or etc., are not affected. The adversarial samples generated by our proposed algorithm reduce the risk of malicious tampering and abuse of images. For the mainstream image translation models StarGAN, STGAN and StarGAN-v2, the attack success rates of the adversarial images generated by the algorithm are 100%, 66.67%, and 73.33%, respectively. It can be seen that the algorithm in this paper has obvious effects on protecting the reasonable and safe use of multimedia resources on social platforms." @default.
- W3132130305 created "2021-03-01" @default.
- W3132130305 creator A5021261089 @default.
- W3132130305 creator A5024199049 @default.
- W3132130305 creator A5048936753 @default.
- W3132130305 creator A5060773798 @default.
- W3132130305 date "2020-12-18" @default.
- W3132130305 modified "2023-09-25" @default.
- W3132130305 title "Adversarial Attacks For Multi Target Image Translation Networks" @default.
- W3132130305 cites W2594717275 @default.
- W3132130305 cites W2811414481 @default.
- W3132130305 cites W2883861033 @default.
- W3132130305 cites W2939645724 @default.
- W3132130305 cites W2962793481 @default.
- W3132130305 cites W2963564844 @default.
- W3132130305 cites W2963626105 @default.
- W3132130305 cites W2963767194 @default.
- W3132130305 cites W2963800363 @default.
- W3132130305 cites W2969416221 @default.
- W3132130305 cites W3028481464 @default.
- W3132130305 cites W3034577585 @default.
- W3132130305 cites W3034600949 @default.
- W3132130305 cites W3127084502 @default.
- W3132130305 doi "https://doi.org/10.1109/pic50277.2020.9350768" @default.
- W3132130305 hasPublicationYear "2020" @default.
- W3132130305 type Work @default.
- W3132130305 sameAs 3132130305 @default.
- W3132130305 citedByCount "3" @default.
- W3132130305 countsByYear W31321303052021 @default.
- W3132130305 countsByYear W31321303052022 @default.
- W3132130305 countsByYear W31321303052023 @default.
- W3132130305 crossrefType "proceedings-article" @default.
- W3132130305 hasAuthorship W3132130305A5021261089 @default.
- W3132130305 hasAuthorship W3132130305A5024199049 @default.
- W3132130305 hasAuthorship W3132130305A5048936753 @default.
- W3132130305 hasAuthorship W3132130305A5060773798 @default.
- W3132130305 hasConcept C104317684 @default.
- W3132130305 hasConcept C105580179 @default.
- W3132130305 hasConcept C115961682 @default.
- W3132130305 hasConcept C119857082 @default.
- W3132130305 hasConcept C126780896 @default.
- W3132130305 hasConcept C149364088 @default.
- W3132130305 hasConcept C154945302 @default.
- W3132130305 hasConcept C185592680 @default.
- W3132130305 hasConcept C194257627 @default.
- W3132130305 hasConcept C2776257435 @default.
- W3132130305 hasConcept C2779757391 @default.
- W3132130305 hasConcept C31258907 @default.
- W3132130305 hasConcept C31972630 @default.
- W3132130305 hasConcept C37736160 @default.
- W3132130305 hasConcept C38652104 @default.
- W3132130305 hasConcept C39890363 @default.
- W3132130305 hasConcept C41008148 @default.
- W3132130305 hasConcept C55493867 @default.
- W3132130305 hasConcept C80444323 @default.
- W3132130305 hasConceptScore W3132130305C104317684 @default.
- W3132130305 hasConceptScore W3132130305C105580179 @default.
- W3132130305 hasConceptScore W3132130305C115961682 @default.
- W3132130305 hasConceptScore W3132130305C119857082 @default.
- W3132130305 hasConceptScore W3132130305C126780896 @default.
- W3132130305 hasConceptScore W3132130305C149364088 @default.
- W3132130305 hasConceptScore W3132130305C154945302 @default.
- W3132130305 hasConceptScore W3132130305C185592680 @default.
- W3132130305 hasConceptScore W3132130305C194257627 @default.
- W3132130305 hasConceptScore W3132130305C2776257435 @default.
- W3132130305 hasConceptScore W3132130305C2779757391 @default.
- W3132130305 hasConceptScore W3132130305C31258907 @default.
- W3132130305 hasConceptScore W3132130305C31972630 @default.
- W3132130305 hasConceptScore W3132130305C37736160 @default.
- W3132130305 hasConceptScore W3132130305C38652104 @default.
- W3132130305 hasConceptScore W3132130305C39890363 @default.
- W3132130305 hasConceptScore W3132130305C41008148 @default.
- W3132130305 hasConceptScore W3132130305C55493867 @default.
- W3132130305 hasConceptScore W3132130305C80444323 @default.
- W3132130305 hasFunder F4320335787 @default.
- W3132130305 hasLocation W31321303051 @default.
- W3132130305 hasOpenAccess W3132130305 @default.
- W3132130305 hasPrimaryLocation W31321303051 @default.
- W3132130305 hasRelatedWork W2756086561 @default.
- W3132130305 hasRelatedWork W2803984336 @default.
- W3132130305 hasRelatedWork W2904276469 @default.
- W3132130305 hasRelatedWork W2963073614 @default.
- W3132130305 hasRelatedWork W2964329690 @default.
- W3132130305 hasRelatedWork W3094011899 @default.
- W3132130305 hasRelatedWork W3178813832 @default.
- W3132130305 hasRelatedWork W4254389809 @default.
- W3132130305 hasRelatedWork W4312525628 @default.
- W3132130305 hasRelatedWork W4323537755 @default.
- W3132130305 isParatext "false" @default.
- W3132130305 isRetracted "false" @default.
- W3132130305 magId "3132130305" @default.
- W3132130305 workType "article" @default.