.png){kind=icon}
返回
Object-attentional untargeted adversarial attack
.png){kind=icon}
OA
AI
DOI：10.1016/j.jisa.2024.103710.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks are facing severe threats from adversarial attacks. Most existing black -box attacks fool the target model by generating either global perturbations or local patches. However, both global perturbations and local patches easily cause annoying visual artifacts in the adversarial example. Compared with some smooth regions of an image, the object region generally has more edges and a more complex texture. Thus, small perturbations on it will be more imperceptible. On the other hand, the object region is undoubtedly the decisive part of an image to classification tasks. Motivated by these two facts, we propose an objectattentional adversarial attack method for untargeted attacks. Specifically, we first generate an object region by intersecting the object detection region from YOLOv4 with the salient object detection (SOD) region from HVPNet. Furthermore, we design an activation strategy to avoid the reaction caused by the incomplete SOD. Then, we perform an adversarial attack only on the detected object region by leveraging a Simple Black -box Adversarial Attack (SimBA). To verify the proposed method, we create a unique dataset by extracting all the images containing the object defined by COCO from ImageNet-1K, named COCO-Reduced-ImageNet in this paper. Experimental results on ImageNet-1K and COCO-Reduced-ImageNet show that under various system settings, our method yields the adversarial example with better perceptual quality while saving the query budget up to 24.16% compared to the state-of-the-art approaches including SimBA. The code is available at https://github.com/GZHU-DVL/OA.
Keyword:
Adversarial attack
Object detection
Salient object detection
Object region
Activation factor
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.7
论文数:
2.0K
被引数:
4.9K
机构
引用论文
LID, LEED, and Alternative Rating Systems—Integrating Low Impact Development Techniques with Green Building DesignLID，LEED和替代评级系统-将低影响开发技术与绿色建筑设计相结合
PREAI
分享收藏Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏A New Aggregation of DNN Sparse and Dense Labeling for Saliency Detection用于显著性检测的DNN稀疏和密集标记的新聚合
PREAI
分享收藏
Numerical and experimental investigations of the shaft-clinching assembly process of automobile wheel-hub-bearing units.png)
Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile EngineeringIF0
PREAI
分享收藏
查看更多内容