WEKO3
アイテム
Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
http://hdl.handle.net/10228/00008090
http://hdl.handle.net/10228/00008090dea5f809-a015-4616-87c4-2305ea61dc36
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
journal.pone.0243963.pdf (5.7 MB)
|
|
| アイテムタイプ | 学術雑誌論文 = Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2021-03-22 | |||||||||||||
| 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 | Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 著者 |
Hirano, Hokuto
× Hirano, Hokuto× Koga, Kazuki× 竹本, 和広
WEKO
24877
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Owing the epidemic of the novel coronavirus disease 2019 (COVID-19), chest X-ray computed tomography imaging is being used for effectively screening COVID-19 patients. The development of computer-aided systems based on deep neural networks (DNNs) has become an advanced open source to rapidly and accurately detect COVID-19 cases because the need for expert radiologists, who are limited in number, forms a bottleneck for screening. However, thus far, the vulnerability of DNN-based systems has been poorly evaluated, although realistic and high-risk attacks using universal adversarial perturbation (UAP), a single (input image agnostic) perturbation that can induce DNN failure in most classification tasks, are available. Thus, we focus on representative DNN models for detecting COVID-19 cases from chest X-ray images and evaluate their vulnerability to UAPs. We consider non-targeted UAPs, which cause a task failure, resulting in an input being assigned an incorrect label, and targeted UAPs, which cause the DNN to classify an input into a specific class. The results demonstrate that the models are vulnerable to non-targeted and targeted UAPs, even in the case of small UAPs. In particular, the 2% norm of the UAPs to the average norm of an image in the image dataset achieves >85% and >90% success rates for the non-targeted and targeted attacks, respectively. Owing to the non-targeted UAPs, the DNN models judge most chest X-ray images as COVID-19 cases. The targeted UAPs allow the DNN models to classify most chest X-ray images into a specified target class. The results indicate that careful consideration is required in practical applications of DNNs to COVID-19 diagnosis; in particular, they emphasize the need for strategies to address security concerns. As an example, we show that iterative fine-tuning of DNN models using UAPs improves the robustness of DNN models against UAPs. | |||||||||||||
| 言語 | en | |||||||||||||
| 書誌情報 |
en : PLoS ONE 巻 15, 号 12, p. e0243963, 発行日 2020-12-17 |
|||||||||||||
| 出版社 | ||||||||||||||
| 出版者 | Public Library of Science | |||||||||||||
| 言語 | en | |||||||||||||
| DOI | ||||||||||||||
| 関連タイプ | isIdenticalTo | |||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.1371/journal.pone.0243963 | |||||||||||||
| 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 | 1932-6203 | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報 | Copyright (c) 2020 Hirano et al. | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報Resource | http://creativecommons.org/licenses/by/4.0/ | |||||||||||||
| 権利情報 | This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. (http://creativecommons.org/licenses/by/4.0/) | |||||||||||||
| 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 | 10360383 | |||||||||||||
| 連携ID | ||||||||||||||
| 値 | 8618 | |||||||||||||
