Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385339737> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4385339737 endingPage "16" @default.
- W4385339737 startingPage "3" @default.
- W4385339737 abstract "In these last years, neural networks are becoming the basis for different kinds of applications and this is mainly due to the stunning performances they offer. Nevertheless, all that glitters is not gold: such tools have demonstrated to be highly sensitive to malicious approaches such as gradient manipulation or the injection of adversarial samples. In particular, another kind of attack that can be performed is to poison a neural network during the training time by injecting a perceptually barely visible trigger signal in a small portion of the dataset (target class), to actually create a backdoor into the trained model. Such a backdoor can be then exploited to redirect all the predictions to the chosen target class at test time. In this work, a novel backdoor attack which resorts to image watermarking algorithms to generate a trigger signal is presented. The watermark signal is almost unperceivable and is embedded in a portion of images of the target class; two different watermarking algorithms have been tested. Experimental results carried out on datasets like MNIST and GTSRB provide satisfactory performances in terms of attack success rate and introduced distortion." @default.
- W4385339737 created "2023-07-29" @default.
- W4385339737 creator A5030121038 @default.
- W4385339737 creator A5038570344 @default.
- W4385339737 creator A5075542490 @default.
- W4385339737 date "2023-01-01" @default.
- W4385339737 modified "2023-09-26" @default.
- W4385339737 title "Image Watermarking Backdoor Attacks in CNN-Based Classification Tasks" @default.
- W4385339737 cites W1513782901 @default.
- W4385339737 cites W2002427601 @default.
- W4385339737 cites W2116467012 @default.
- W4385339737 cites W2399587145 @default.
- W4385339737 cites W2748789698 @default.
- W4385339737 cites W2809895662 @default.
- W4385339737 cites W2964043980 @default.
- W4385339737 cites W2964121744 @default.
- W4385339737 cites W2970335439 @default.
- W4385339737 cites W3212158867 @default.
- W4385339737 cites W3217308368 @default.
- W4385339737 cites W4286979592 @default.
- W4385339737 doi "https://doi.org/10.1007/978-3-031-37745-7_1" @default.
- W4385339737 hasPublicationYear "2023" @default.
- W4385339737 type Work @default.
- W4385339737 citedByCount "0" @default.
- W4385339737 crossrefType "book-chapter" @default.
- W4385339737 hasAuthorship W4385339737A5030121038 @default.
- W4385339737 hasAuthorship W4385339737A5038570344 @default.
- W4385339737 hasAuthorship W4385339737A5075542490 @default.
- W4385339737 hasConcept C115961682 @default.
- W4385339737 hasConcept C126780896 @default.
- W4385339737 hasConcept C150817343 @default.
- W4385339737 hasConcept C153180895 @default.
- W4385339737 hasConcept C154945302 @default.
- W4385339737 hasConcept C164112704 @default.
- W4385339737 hasConcept C190502265 @default.
- W4385339737 hasConcept C194257627 @default.
- W4385339737 hasConcept C199360897 @default.
- W4385339737 hasConcept C2776257435 @default.
- W4385339737 hasConcept C2777212361 @default.
- W4385339737 hasConcept C2779843651 @default.
- W4385339737 hasConcept C2781045450 @default.
- W4385339737 hasConcept C31258907 @default.
- W4385339737 hasConcept C31972630 @default.
- W4385339737 hasConcept C38652104 @default.
- W4385339737 hasConcept C41008148 @default.
- W4385339737 hasConcept C50644808 @default.
- W4385339737 hasConceptScore W4385339737C115961682 @default.
- W4385339737 hasConceptScore W4385339737C126780896 @default.
- W4385339737 hasConceptScore W4385339737C150817343 @default.
- W4385339737 hasConceptScore W4385339737C153180895 @default.
- W4385339737 hasConceptScore W4385339737C154945302 @default.
- W4385339737 hasConceptScore W4385339737C164112704 @default.
- W4385339737 hasConceptScore W4385339737C190502265 @default.
- W4385339737 hasConceptScore W4385339737C194257627 @default.
- W4385339737 hasConceptScore W4385339737C199360897 @default.
- W4385339737 hasConceptScore W4385339737C2776257435 @default.
- W4385339737 hasConceptScore W4385339737C2777212361 @default.
- W4385339737 hasConceptScore W4385339737C2779843651 @default.
- W4385339737 hasConceptScore W4385339737C2781045450 @default.
- W4385339737 hasConceptScore W4385339737C31258907 @default.
- W4385339737 hasConceptScore W4385339737C31972630 @default.
- W4385339737 hasConceptScore W4385339737C38652104 @default.
- W4385339737 hasConceptScore W4385339737C41008148 @default.
- W4385339737 hasConceptScore W4385339737C50644808 @default.
- W4385339737 hasLocation W43853397371 @default.
- W4385339737 hasOpenAccess W4385339737 @default.
- W4385339737 hasPrimaryLocation W43853397371 @default.
- W4385339737 hasRelatedWork W1587163475 @default.
- W4385339737 hasRelatedWork W2100567952 @default.
- W4385339737 hasRelatedWork W2148446898 @default.
- W4385339737 hasRelatedWork W2367449261 @default.
- W4385339737 hasRelatedWork W2385289568 @default.
- W4385339737 hasRelatedWork W2952348804 @default.
- W4385339737 hasRelatedWork W3046850722 @default.
- W4385339737 hasRelatedWork W3173775589 @default.
- W4385339737 hasRelatedWork W4321352652 @default.
- W4385339737 hasRelatedWork W2134804386 @default.
- W4385339737 isParatext "false" @default.
- W4385339737 isRetracted "false" @default.
- W4385339737 workType "book-chapter" @default.