对抗制
可转让性
计算机科学
人工智能
稳健性(进化)
面部识别系统
深层神经网络
面子(社会学概念)
保护
梯度下降
机器学习
深度学习
模式识别(心理学)
人工神经网络
计算机视觉
医学
社会科学
生物化学
化学
护理部
罗伊特
社会学
基因
作者
Shuangliang Li,Jinwei Wang,Hao Wu,Jiawei Zhang,Xin Cheng,Xiangyang Luo,Bin Ma
标识
DOI:10.1109/tai.2025.3527923
摘要
Face Recognition (FR) systems, while widely used across various sectors, are vulnerable to adversarial attacks, particularly those based on deep neural networks. Despite existing efforts to enhance the robustness of FR models, they still face the risk of secondary adversarial attacks. To address this, we propose a novel approach employing "strengthened face" with preemptive defensive perturbations. Strengthened face ensures original recognition accuracy while safeguarding FR systems against secondary attacks. In the white-box scenario, the strengthened face utilizes gradient-based and optimization-based methods to minimize feature representation differences between face pairs. For the black-box scenario, we propose Shielded Gradient Sign Descent (SGSD) to optimize the gradient update direction of strengthened faces, ensuring the transferability and effectiveness against unknown adversarial attacks. Experimental results demonstrate the efficacy of strengthened faces in defending against adversarial faces without compromising the performance of FR models or face image visual quality. Moreover, SGSD outperforms conventional methods, achieving an average performance improvement of 4% in transferability across different attack intensities.
科研通智能强力驱动
Strongly Powered by AbleSci AI