Modifying the one-hot encoding technique can enhance the adversarial robustness of the visual model for symbol recognition
-
Published:2024-09
Issue:
Volume:250
Page:123751
-
ISSN:0957-4174
-
Container-title:Expert Systems with Applications
-
language:en
-
Short-container-title:Expert Systems with Applications
Author:
Sun YiORCID,
Zheng Jun,
Zhao Hanyu,
Zhou HuipengORCID,
Li JiaxingORCID,
Li FanORCID,
Xiong Zehui,
Liu Jun,
Li Yuanzhang
Reference60 articles.
1. Adversarial example detection for dnn models: A review and experimental comparison;Aldahdooh;Artificial Intelligence Review,2022
2. The architecture of cognition;Anderson,1996
3. Andriushchenko, M., Croce, F., Flammarion, N., & Hein, M. (2020). Square attack: A query-efficient black-box adversarial attack via random search. In European conference on computer vision (pp. 484–501).
4. Working memory;Baddeley;Science,1992
5. Borkar, T., Heide, F., & Karam, L. (2020). Defending against universal attacks through selective feature regeneration. In Proceedings of IEEE/CVF conference on computer vision and pattern recognition (pp. 709–719).