Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294691188> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4294691188 abstract "Recently, a number of researches have been proposed to protect the intellectual property (IP) of Deep Neural Network (DNN) models. However, most existing works are passive protection methods as they attempt to extract watermark from the pirated model after piracy occurs. In this paper, we propose an active IP protection method for DNN in which we utilize a variant of sample-specific backdoor attack to implement active authorization control for DNN models. During training, we mislabel all the clean images and keep the labels of backdoor instances as their ground-truth labels. Different from general backdoor trigger, we train a U-Net model to generate sample-specific trigger. This kind of trigger is sample-specific and invisible, which works as the secret key for each image and is hard to be noticed. Moreover, compared with existing active DNN IP protection methods, the proposed method can be applied in the black-box scenario. Experimental results on ImageNet and YouTube Aligned Face datasets demonstrate the effectiveness and robustness of the proposed method." @default.
- W4294691188 created "2022-09-06" @default.
- W4294691188 creator A5022068526 @default.
- W4294691188 creator A5024861014 @default.
- W4294691188 creator A5028385393 @default.
- W4294691188 creator A5083275572 @default.
- W4294691188 creator A5085698418 @default.
- W4294691188 date "2022-06-13" @default.
- W4294691188 modified "2023-09-23" @default.
- W4294691188 title "Sample-Specific Backdoor based Active Intellectual Property Protection for Deep Neural Networks" @default.
- W4294691188 cites W2019464758 @default.
- W4294691188 cites W2108598243 @default.
- W4294691188 cites W2194775991 @default.
- W4294691188 cites W2325939864 @default.
- W4294691188 cites W2563117427 @default.
- W4294691188 cites W2768064608 @default.
- W4294691188 cites W2806082141 @default.
- W4294691188 cites W2914330473 @default.
- W4294691188 cites W3034856584 @default.
- W4294691188 cites W3081073185 @default.
- W4294691188 cites W3131700981 @default.
- W4294691188 cites W3179479348 @default.
- W4294691188 cites W4214680449 @default.
- W4294691188 cites W4220734716 @default.
- W4294691188 doi "https://doi.org/10.1109/aicas54282.2022.9869927" @default.
- W4294691188 hasPublicationYear "2022" @default.
- W4294691188 type Work @default.
- W4294691188 citedByCount "0" @default.
- W4294691188 crossrefType "proceedings-article" @default.
- W4294691188 hasAuthorship W4294691188A5022068526 @default.
- W4294691188 hasAuthorship W4294691188A5024861014 @default.
- W4294691188 hasAuthorship W4294691188A5028385393 @default.
- W4294691188 hasAuthorship W4294691188A5083275572 @default.
- W4294691188 hasAuthorship W4294691188A5085698418 @default.
- W4294691188 hasConcept C104317684 @default.
- W4294691188 hasConcept C108759981 @default.
- W4294691188 hasConcept C111472728 @default.
- W4294691188 hasConcept C111919701 @default.
- W4294691188 hasConcept C115961682 @default.
- W4294691188 hasConcept C119857082 @default.
- W4294691188 hasConcept C138885662 @default.
- W4294691188 hasConcept C150817343 @default.
- W4294691188 hasConcept C154945302 @default.
- W4294691188 hasConcept C185592680 @default.
- W4294691188 hasConcept C189950617 @default.
- W4294691188 hasConcept C198531522 @default.
- W4294691188 hasConcept C26517878 @default.
- W4294691188 hasConcept C2781045450 @default.
- W4294691188 hasConcept C2984842247 @default.
- W4294691188 hasConcept C34974158 @default.
- W4294691188 hasConcept C38652104 @default.
- W4294691188 hasConcept C41008148 @default.
- W4294691188 hasConcept C43617362 @default.
- W4294691188 hasConcept C50644808 @default.
- W4294691188 hasConcept C55493867 @default.
- W4294691188 hasConcept C63479239 @default.
- W4294691188 hasConceptScore W4294691188C104317684 @default.
- W4294691188 hasConceptScore W4294691188C108759981 @default.
- W4294691188 hasConceptScore W4294691188C111472728 @default.
- W4294691188 hasConceptScore W4294691188C111919701 @default.
- W4294691188 hasConceptScore W4294691188C115961682 @default.
- W4294691188 hasConceptScore W4294691188C119857082 @default.
- W4294691188 hasConceptScore W4294691188C138885662 @default.
- W4294691188 hasConceptScore W4294691188C150817343 @default.
- W4294691188 hasConceptScore W4294691188C154945302 @default.
- W4294691188 hasConceptScore W4294691188C185592680 @default.
- W4294691188 hasConceptScore W4294691188C189950617 @default.
- W4294691188 hasConceptScore W4294691188C198531522 @default.
- W4294691188 hasConceptScore W4294691188C26517878 @default.
- W4294691188 hasConceptScore W4294691188C2781045450 @default.
- W4294691188 hasConceptScore W4294691188C2984842247 @default.
- W4294691188 hasConceptScore W4294691188C34974158 @default.
- W4294691188 hasConceptScore W4294691188C38652104 @default.
- W4294691188 hasConceptScore W4294691188C41008148 @default.
- W4294691188 hasConceptScore W4294691188C43617362 @default.
- W4294691188 hasConceptScore W4294691188C50644808 @default.
- W4294691188 hasConceptScore W4294691188C55493867 @default.
- W4294691188 hasConceptScore W4294691188C63479239 @default.
- W4294691188 hasFunder F4320321001 @default.
- W4294691188 hasLocation W42946911881 @default.
- W4294691188 hasOpenAccess W4294691188 @default.
- W4294691188 hasPrimaryLocation W42946911881 @default.
- W4294691188 hasRelatedWork W1481179460 @default.
- W4294691188 hasRelatedWork W2042311553 @default.
- W4294691188 hasRelatedWork W2360824522 @default.
- W4294691188 hasRelatedWork W2363475415 @default.
- W4294691188 hasRelatedWork W3046850722 @default.
- W4294691188 hasRelatedWork W3173775589 @default.
- W4294691188 hasRelatedWork W4226083115 @default.
- W4294691188 hasRelatedWork W4288322434 @default.
- W4294691188 hasRelatedWork W4317664613 @default.
- W4294691188 hasRelatedWork W1629725936 @default.
- W4294691188 isParatext "false" @default.
- W4294691188 isRetracted "false" @default.
- W4294691188 workType "article" @default.