自动化学报2026，Vol.52Issue(4)：693-708,16.DOI:10.16383/j.aas.c250300
针对目标检测的可迁移性对抗补丁生成方法
A Transferable Adversarial Patch Generation Method for Object Detection
摘要
Abstract
With the widespread deployment of object detection models in real-world applications,their security is-sues have increasingly become a research focus.Adversarial attack techniques,by carefully designing adversarial patches,can effectively induce models to produce erroneous predictions,thereby revealing the inherent vulnerabilit-ies of deep neural networks in the decision-making process.To enhance the transferability of adversarial patches across different detectors,most existing methods rely on static weight fusion strategies for joint optimization.However,such approaches struggle to fully reconcile the discrepancies in vulnerability distributions and optimiza-tion dynamics among detectors,leading to imbalanced attack effectiveness across models and significantly limiting the transferability.To address this challenge,this paper proposes a transferable adversarial patch generation frame-work based on a multi-task dynamic reweighting mechanism.The framework introduces a global correction factor and a local correction factor,which dynamically adjust task weights from two perspectives:The overall optimiza-tion progress among tasks and the fine-grained convergence behavior of individual tasks.This design enables better coordination and improved robustness during multi-model joint optimization.Extensive experiments in both the di-gital and physical domains demonstrate that the proposed method significantly enhances the adversarial transferab-ility of patches across various object detectors and achieves strong attack performance in deployments under real-world physical domain.关键词
目标检测/对抗攻击/跨模型攻击/动态重加权/攻击迁移性Key words
object detection/adversarial attack/cross-model attack/dynamic reweighting/attack transferability引用本文复制引用
燕庆龙,向昕宇,张浩,马佳义..针对目标检测的可迁移性对抗补丁生成方法[J].自动化学报,2026,52(4):693-708,16.基金项目
国家自然科学基金(U23B2050,62473297)资助 Supported by National Natural Science Foundation of China(U23B2050,62473297) （U23B2050,62473297）
