WEKO3
アイテム
Backdoor Attacks on Deep Neural Networks via Transfer Learning from Natural Images
http://hdl.handle.net/10228/00009030
http://hdl.handle.net/10228/00009030138f15ce-4784-4c7e-8b77-0798ad935e1a
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
applsci-12-12564-with-cover.pdf (287.0 kB)
|
|
| アイテムタイプ | 学術雑誌論文 = Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2022-12-09 | |||||||||||||
| 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 | Backdoor Attacks on Deep Neural Networks via Transfer Learning from Natural Images | |||||||||||||
| 言語 | en | |||||||||||||
| その他のタイトル | ||||||||||||||
| その他のタイトル | Backdoor attacks on deep neural networks via transfer learning from natural images | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 著者 |
Matsuo, Yuki
× Matsuo, Yuki× 竹本, 和広
WEKO
24877
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Backdoor attacks are a serious security threat to open-source and outsourced development of computational systems based on deep neural networks (DNNs). In particular, the transferability of backdoors is remarkable; that is, they can remain effective after transfer learning is performed. Given that transfer learning from natural images is widely used in real-world applications, the question of whether backdoors can be transferred from neural models pretrained on natural images involves considerable security implications. However, this topic has not been evaluated rigorously in prior studies. Hence, in this study, we configured backdoors in 10 representative DNN models pretrained on a natural image dataset, and then fine-tuned the backdoored models via transfer learning for four real-world applications, including pneumonia classification from chest X-ray images, emergency response monitoring from aerial images, facial recognition, and age classification from images of faces. Our experimental results show that the backdoors generally remained effective after transfer learning from natural images, except for small DNN models. Moreover, the backdoors were difficult to detect using a common method. Our findings indicate that backdoor attacks can exhibit remarkable transferability in more realistic transfer learning processes, and highlight the need for the development of more advanced security countermeasures in developing systems using DNN models for sensitive or mission-critical applications. | |||||||||||||
| 言語 | en | |||||||||||||
| 書誌情報 |
en : Applied Sciences 巻 12, 号 24, p. 12564-1-12564-9, 発行日 2022-12-08 |
|||||||||||||
| 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/app122412564 | |||||||||||||
| 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 | 2076-3417 | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報Resource | https://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 | backdoor attacks | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | transfer learning | |||||||||||||
| 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 | 10405256 | |||||||||||||
| 連携ID | ||||||||||||||
| 値 | 10999 | |||||||||||||
