.png){kind=icon}
返回
Attention-guided evolutionary attack with elastic-net regularization on face recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109760.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, face recognition has achieved promising results along with the development of advanced Deep Neural Networks (DNNs). The existing face recognition systems are vulnerable to adversarial examples, which brings potential security risks. Evolutionary Attack (EA) has been successfully used to fool face recognition by inducing a minimum perturbation to a face image with few queries. However, EA employs the global information of face images but ignores their local characteristics. In addition, restricting the & POUND; 2-norm of adversarial perturbations hinders the diversity of adversarial perturbations. To solve the above problems, we propose Attention-guided Evolutionary Attack with Elastic-Net Regularization (ER AEA) for attacking face recognition. ERAEA extracts local facial characteristics by attention mechanism, effectively im proving the attack effect and image perception quality. In particular, ERAEA adopts an attention mechanism to guide evolutionary direction, which operates on the covariance matrix as it contains crucial information about the evolutionary path. Furthermore, we design an adaptive elastic-net regularization to diversify the adversarial perturbation, accelerating the optimization performance. Extensive experiments obtained on three benchmarks demonstrate that our proposed method achieves better perturbation norm than the state-of-the-art methods with limited queries on face recognition and generates adversarial face images with higher perceptual quality. Besides, ERAEA requires fewer queries to achieve a fixed adversarial perturbation norm.& COPY; 2023 Elsevier Ltd. All rights reserved.
Keyword:
Face recognition
Convolutional neural networks
Adversarial examples
Evolutionary attack
Attention mechanisms
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Evaluation of uncertainty in input parameters to pharmacokinetic models and the resulting uncertainty in output评估药代动力学模型输入参数的不确定性以及由此产生的输出不确定性
PREAI
分享收藏Noise-robust dictionary learning with slack block-Diagonal structure for face recognition用于人脸识别的具有松弛块对角结构的噪声鲁棒字典学习.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容