WEKO3
アイテム
Simple Black-Box Universal Adversarial Attacks on Deep Neural Networks for Medical Image Classification
http://hdl.handle.net/10228/00008822
http://hdl.handle.net/10228/00008822c5717a23-338d-4a27-8852-e3862c2e262c
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
algorithms-15-00144-v2.pdf (2.1 MB)
|
|
| アイテムタイプ | 学術雑誌論文 = Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2022-04-25 | |||||||||||||
| 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 | Simple Black-Box Universal Adversarial Attacks on Deep Neural Networks for Medical Image Classification | |||||||||||||
| 言語 | en | |||||||||||||
| その他のタイトル | ||||||||||||||
| その他のタイトル | Simple black-box universal adversarial attacks on deep neural networks for medical image classification | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 著者 |
Koga, Kazuki
× Koga, Kazuki× 竹本, 和広
WEKO
24877
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Universal adversarial attacks, which hinder most deep neural network (DNN) tasks using only a single perturbation called universal adversarial perturbation (UAP), are a realistic security threat to the practical application of a DNN for medical imaging. Given that computer-based systems are generally operated under a black-box condition in which only input queries are allowed and outputs are accessible, the impact of UAPs seems to be limited because well-used algorithms for generating UAPs are limited to white-box conditions in which adversaries can access model parameters. Nevertheless, we propose a method for generating UAPs using a simple hill-climbing search based only on DNN outputs to demonstrate that UAPs are easily generatable using a relatively small dataset under black-box conditions with representative DNN-based medical image classifications. Black-box UAPs can be used to conduct both nontargeted and targeted attacks. Overall, the black-box UAPs showed high attack success rates (40–90%). The vulnerability of the black-box UAPs was observed in several model architectures. The results indicate that adversaries can also generate UAPs through a simple procedure under the black-box condition to foil or control diagnostic medical imaging systems based on DNNs, and that UAPs are a more serious security threat. | |||||||||||||
| 言語 | en | |||||||||||||
| 書誌情報 |
en : Algorithms 巻 15, 号 5, p. 144-1-144-12, 発行日 2022-04-22 |
|||||||||||||
| 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/a15050144 | |||||||||||||
| 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 | 1999-4893 | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報 | 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 (https://creativecommons.org/licenses/by/4.0/). | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | black-box algorithm | |||||||||||||
| 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 | adversarial attacks | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | medical imaging | |||||||||||||
| 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 | 10391182 | |||||||||||||
| 連携ID | ||||||||||||||
| 値 | 10375 | |||||||||||||
