Thông tin tài liệu
Thông tin siêu dữ liệu biểu ghi
Trường DC | Giá trị | Ngôn ngữ |
---|---|---|
dc.contributor.author | Zhiquan, He | - |
dc.contributor.author | Xujia, Lan | - |
dc.contributor.author | Jianhe, Yuan | - |
dc.date.accessioned | 2023-03-31T07:01:41Z | - |
dc.date.available | 2023-03-31T07:01:41Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | https://link.springer.com/article/10.1007/s10489-022-03838-0 | - |
dc.identifier.uri | https://dlib.phenikaa-uni.edu.vn/handle/PNK/7382 | - |
dc.description | CC BY | vi |
dc.description.abstract | Adversarial attack aims to fail the deep neural network by adding a small amount of perturbation to the input image, in which the attack success rate and resulting image quality are maximized under the lp norm perturbation constraint. However, the lp norm is not accurately correlated to human perception of image quality. Attack methods based on l0 norm constraint usually suffer from the high computational cost due to the iterative search for candidate pixels to modify. | vi |
dc.language.iso | en | vi |
dc.publisher | Springer | vi |
dc.subject | deep neural network | vi |
dc.subject | norm perturbation constraint | vi |
dc.title | Multi-layer noise reshaping and perceptual optimization for effective adversarial attack of images | vi |
dc.type | Book | vi |
Bộ sưu tập | OER - Công nghệ thông tin |
Danh sách tệp tin đính kèm: