Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381572307> ?p ?o ?g. }
- W4381572307 endingPage "6588" @default.
- W4381572307 startingPage "6588" @default.
- W4381572307 abstract "Deep steganography (DS), using neural networks to hide one image in another, has performed well in terms of invisibility, embedding capacity, etc. Current steganalysis methods for DS can only detect or remove secret images hidden in natural images and cannot analyze or modify secret content. Our technique is the first approach to not only effectively prevent covert communications using DS, but also analyze and modify the content of covert communications. We proposed a novel adversarial attack method for DS considering both white-box and black-box scenarios. For the white-box attack, several novel loss functions were applied to construct a gradient- and optimizer-based adversarial attack that could delete and modify secret images. As a more realistic case, a black-box method was proposed based on surrogate training and a knowledge distillation technique. All methods were tested on the Tiny ImageNet and MS COCO datasets. The experimental results showed that the proposed attack method could completely remove or even modify the secret image in the container image while maintaining the latter’s high quality. More importantly, the proposed adversarial attack method can also be regarded as a new DS approach." @default.
- W4381572307 created "2023-06-22" @default.
- W4381572307 creator A5000462480 @default.
- W4381572307 creator A5002721866 @default.
- W4381572307 creator A5002971389 @default.
- W4381572307 creator A5069061259 @default.
- W4381572307 creator A5070575632 @default.
- W4381572307 creator A5084574767 @default.
- W4381572307 date "2023-05-29" @default.
- W4381572307 modified "2023-09-27" @default.
- W4381572307 title "Adversarial Attack for Deep Steganography Based on Surrogate Training and Knowledge Diffusion" @default.
- W4381572307 cites W1855479288 @default.
- W4381572307 cites W1861492603 @default.
- W4381572307 cites W1955882805 @default.
- W4381572307 cites W2064076387 @default.
- W4381572307 cites W2133665775 @default.
- W4381572307 cites W2161022751 @default.
- W4381572307 cites W2508457857 @default.
- W4381572307 cites W2541505803 @default.
- W4381572307 cites W2543927648 @default.
- W4381572307 cites W2746600820 @default.
- W4381572307 cites W2774018344 @default.
- W4381572307 cites W2774644650 @default.
- W4381572307 cites W2883233582 @default.
- W4381572307 cites W2900141423 @default.
- W4381572307 cites W2917640112 @default.
- W4381572307 cites W2919023666 @default.
- W4381572307 cites W2952651666 @default.
- W4381572307 cites W2963178695 @default.
- W4381572307 cites W2963726920 @default.
- W4381572307 cites W2963857521 @default.
- W4381572307 cites W2969664989 @default.
- W4381572307 cites W2997583194 @default.
- W4381572307 cites W3021799630 @default.
- W4381572307 cites W3034856584 @default.
- W4381572307 cites W3035569111 @default.
- W4381572307 cites W3035671550 @default.
- W4381572307 cites W3055851871 @default.
- W4381572307 cites W3082261099 @default.
- W4381572307 cites W3082778890 @default.
- W4381572307 cites W3097573595 @default.
- W4381572307 cites W3175786209 @default.
- W4381572307 cites W3199558812 @default.
- W4381572307 cites W3209895487 @default.
- W4381572307 cites W4226378932 @default.
- W4381572307 cites W4283512932 @default.
- W4381572307 cites W4291511757 @default.
- W4381572307 cites W4362468139 @default.
- W4381572307 cites W4366966879 @default.
- W4381572307 doi "https://doi.org/10.3390/app13116588" @default.
- W4381572307 hasPublicationYear "2023" @default.
- W4381572307 type Work @default.
- W4381572307 citedByCount "0" @default.
- W4381572307 crossrefType "journal-article" @default.
- W4381572307 hasAuthorship W4381572307A5000462480 @default.
- W4381572307 hasAuthorship W4381572307A5002721866 @default.
- W4381572307 hasAuthorship W4381572307A5002971389 @default.
- W4381572307 hasAuthorship W4381572307A5069061259 @default.
- W4381572307 hasAuthorship W4381572307A5070575632 @default.
- W4381572307 hasAuthorship W4381572307A5084574767 @default.
- W4381572307 hasBestOaLocation W43815723071 @default.
- W4381572307 hasConcept C107368093 @default.
- W4381572307 hasConcept C108583219 @default.
- W4381572307 hasConcept C108801101 @default.
- W4381572307 hasConcept C115961682 @default.
- W4381572307 hasConcept C124101348 @default.
- W4381572307 hasConcept C153180895 @default.
- W4381572307 hasConcept C154945302 @default.
- W4381572307 hasConcept C37736160 @default.
- W4381572307 hasConcept C41008148 @default.
- W4381572307 hasConcept C41608201 @default.
- W4381572307 hasConceptScore W4381572307C107368093 @default.
- W4381572307 hasConceptScore W4381572307C108583219 @default.
- W4381572307 hasConceptScore W4381572307C108801101 @default.
- W4381572307 hasConceptScore W4381572307C115961682 @default.
- W4381572307 hasConceptScore W4381572307C124101348 @default.
- W4381572307 hasConceptScore W4381572307C153180895 @default.
- W4381572307 hasConceptScore W4381572307C154945302 @default.
- W4381572307 hasConceptScore W4381572307C37736160 @default.
- W4381572307 hasConceptScore W4381572307C41008148 @default.
- W4381572307 hasConceptScore W4381572307C41608201 @default.
- W4381572307 hasIssue "11" @default.
- W4381572307 hasLocation W43815723071 @default.
- W4381572307 hasOpenAccess W4381572307 @default.
- W4381572307 hasPrimaryLocation W43815723071 @default.
- W4381572307 hasRelatedWork W1576926746 @default.
- W4381572307 hasRelatedWork W174759733 @default.
- W4381572307 hasRelatedWork W2126313030 @default.
- W4381572307 hasRelatedWork W2359334028 @default.
- W4381572307 hasRelatedWork W2402107956 @default.
- W4381572307 hasRelatedWork W2971349019 @default.
- W4381572307 hasRelatedWork W2974057040 @default.
- W4381572307 hasRelatedWork W2982078027 @default.
- W4381572307 hasRelatedWork W3111851281 @default.
- W4381572307 hasRelatedWork W4232794086 @default.
- W4381572307 hasVolume "13" @default.
- W4381572307 isParatext "false" @default.
- W4381572307 isRetracted "false" @default.