Thông tin chung
  English
  Đề tài NC khoa học
  Bài báo, báo cáo khoa học
  Hướng dẫn Sau đại học
  Sách và giáo trình
  Các học phần và môn giảng dạy
  Giải thưởng khoa học, Phát minh, sáng chế
  Khen thưởng
  Thông tin khác
  Tài liệu tham khảo
  Hiệu chỉnh
 
Số người truy cập: 107,014,117

 Search Space of Adversarial Perturbations Against Image Filters
Tác giả hoặc Nhóm tác giả: Dang Duy Thang and Toshihiro Matsui
Nơi đăng: International Journal of Advanced Computer Science and Applications (ESCI, Scopus); Số: 1 Volume 11, ISSN : 2156-5570;Từ->đến trang: 11-19;Năm: 2020
Lĩnh vực: Công nghệ thông tin; Loại: Bài báo khoa học; Thể loại: Quốc tế
TÓM TẮT
The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to deceive the deep learning system. In this study, we focus on investigating the ability to create adversarial patterns in search space against defensive methods that use image filters. Experimental results conducted on the ImageNet dataset showed the correlation between search space of adversarial perturbation and filters. These findings open a new direction for building stronger offensive methods towards deep learning systems.
ABSTRACT
The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to deceive the deep learning system. In this study, we focus on investigating the ability to create adversarial patterns in search space against defensive methods that use image filters. Experimental results conducted on the ImageNet dataset showed the correlation between search space of adversarial perturbation and filters. These findings open a new direction for building stronger offensive methods towards deep learning systems.
© Đại học Đà Nẵng
 
 
Địa chỉ: 41 Lê Duẩn Thành phố Đà Nẵng
Điện thoại: (84) 0236 3822 041 ; Email: dhdn@ac.udn.vn