信息安全研究2025，Vol.11Issue(3)：221-230,10.DOI:10.12379/j.issn.2096-1057.2025.03.04
基于YOLOv8目标检测器的对抗攻击方案设计
Design of Adversarial Attack Scheme Based on YOLOv8 Object Detector
摘要
Abstract
Currently,cameras equipped with AI object detection technology are widely used.However,AI object detection models in real-world applications are vulnerable to adversarial attacks.Existing adversarial attack methods,primarily designed for earlier models,are ineffective against the latest YOLOv8 object detector.To address this issue,we propose a novel adversarial patch attack method specifically for the YOLOv8 object detector.This method minimizes confidence output while incorporating an exponential moving average(EMA)attention mechanism to enhance feature extraction during patch generation,thereby improving the attack's effectiveness.Experimental results demonstrate that our method achieves superior attack performance and transferability.Validation tests,in which the adversarial patches were printed on clothing,also demonstrated excellent attack results,indicating the strong practicality of our proposed method.关键词
深度学习/对抗样本/YOLOv8/目标检测/对抗补丁Key words
deep learning/adversarial example/YOLOv8/object detection/adversarial patch分类
计算机与自动化引用本文复制引用
李秀滢,赵海淇,陈雪松,张健毅,赵成..基于YOLOv8目标检测器的对抗攻击方案设计[J].信息安全研究,2025,11(3):221-230,10.基金项目
国家档案局科技项目(2022-X-069) （2022-X-069）
北京市自然科学基金项目(4232034) （4232034）
中央高校基本科研业务费专项资金项目(3282023038,328202264,328202241) （3282023038,328202264,328202241）
