1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Towards Adversarial Robustness for Multi-Mode Data through Metric Learning
作者 廖文宏
Liao, Wen-Hung;Khan, Sarwar;Chen, Jun-Cheng;Chen, Chu-Song
貢獻者 資訊系
關鍵詞 adversarial attacks; adversarial training; classification; metric learning; multi-mode; prototypes
日期 2023-07
上傳時間 13-十二月-2023 14:16:36 (UTC+8)
摘要 Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness.
關聯 Sensors, Vol.23, No.13, 6173
資料類型 article
DOI https://doi.org/10.3390/s23136173
dc.contributor 資訊系
dc.creator (作者) 廖文宏
dc.creator (作者) Liao, Wen-Hung;Khan, Sarwar;Chen, Jun-Cheng;Chen, Chu-Song
dc.date (日期) 2023-07
dc.date.accessioned 13-十二月-2023 14:16:36 (UTC+8)-
dc.date.available 13-十二月-2023 14:16:36 (UTC+8)-
dc.date.issued (上傳時間) 13-十二月-2023 14:16:36 (UTC+8)-
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/148734-
dc.description.abstract (摘要) Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness.
dc.format.extent 97 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) Sensors, Vol.23, No.13, 6173
dc.subject (關鍵詞) adversarial attacks; adversarial training; classification; metric learning; multi-mode; prototypes
dc.title (題名) Towards Adversarial Robustness for Multi-Mode Data through Metric Learning
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.3390/s23136173
dc.doi.uri (DOI) https://doi.org/10.3390/s23136173