WEKO3
アイテム
Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks with Transfer Learning
http://hdl.handle.net/10228/00008714
http://hdl.handle.net/10228/00008714e6e0fe5e-a782-4e20-b10e-dabda9e2516f
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
jimaging-08-00038.pdf (3.7 MB)
|
|
| Item type | 学術雑誌論文 = Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2022-02-08 | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks with Transfer Learning | |||||||||||||
| 言語 | en | |||||||||||||
| その他のタイトル | ||||||||||||||
| その他のタイトル | Natural images allow universal adversarial attacks on medical image classification using deep neural networks with transfer learning | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 著者 |
Minagi, Akinori
× Minagi, Akinori× Hirano, Hokuto× 竹本, 和広
WEKO
24877
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Transfer learning from natural images is used in deep neural networks (DNNs) for medical image classification to achieve a computer-aided clinical diagnosis. Although the adversarial vulnerability of DNNs hinders practical applications owing to the high stakes of diagnosis, adversarial attacks are expected to be limited because training datasets (medical images), which are often required for adversarial attacks, are generally unavailable in terms of security and privacy preservation. Nevertheless, in this study, we demonstrated that adversarial attacks are also possible using natural images for medical DNN models with transfer learning, even if such medical images are unavailable; in particular, we showed that universal adversarial perturbations (UAPs) can also be generated from natural images. UAPs from natural images are useful for both non-targeted and targeted attacks. The performance of UAPs from natural images was significantly higher than that of random controls. The use of transfer learning causes a security hole, which decreases the reliability and safety of computer-based disease diagnosis. Model training from random initialization reduced the performance of UAPs from natural images; however, it did not completely avoid vulnerability to UAPs. The vulnerability of UAPs to natural images is expected to become a significant security threat. | |||||||||||||
| 言語 | en | |||||||||||||
| 書誌情報 |
en : Journal of Imaging 巻 8, 号 2, p. 38-1-38-16, 発行日 2022-02-04 |
|||||||||||||
| 出版社 | ||||||||||||||
| 出版者 | MDPI | |||||||||||||
| DOI | ||||||||||||||
| 関連タイプ | isIdenticalTo | |||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.3390/jimaging8020038 | |||||||||||||
| 日本十進分類法 | ||||||||||||||
| 主題Scheme | NDC | |||||||||||||
| 主題 | 548 | |||||||||||||
| ISSN | ||||||||||||||
| 収録物識別子タイプ | EISSN | |||||||||||||
| 収録物識別子 | 2313-433X | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報Resource | http://creativecommons.org/licenses/by/4.0/ | |||||||||||||
| 権利情報 | Copyright (c) 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | deep neural networks | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | transfer learning | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | medical imaging | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | adversarial attacks | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | security and privacy | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | VoR | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||
| 査読の有無 | ||||||||||||||
| 値 | yes | |||||||||||||
| 研究者情報 | ||||||||||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/100000509_ja.html | |||||||||||||
| 論文ID（連携） | ||||||||||||||
| 値 | 10384685 | |||||||||||||
| 連携ID | ||||||||||||||
| 値 | 10117 | |||||||||||||
