arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.21066cs.CVcs.CR
收藏

BadDet+: 用于目标检测的鲁棒后门攻击

BadDet+: Robust Backdoor Attacks for Object Detection

School of Computer Science, Queensland University of Technology, Brisbane Australia(昆士兰科技大学计算机科学学院);Industrial Research Organisation, Pullenvale QLD, Australia(工业研究组织);Centre for Robotics, Queensland University of Technology, Brisbane Australia(机器人中心)

Kealan Dunnett, Reza Arablouei, Dimity Miller, Volkan Dedeoglu, Raja Jurdak

AI总结:

BadDet+提出了一种基于惩罚的框架,统一了区域误分类攻击和目标消失攻击,提升了目标检测在现实环境中的鲁棒性,并揭示了现有检测方法的脆弱性。

摘要:

后门攻击对深度学习构成了严重威胁,但其对目标检测的影响相较于图像分类仍缺乏充分理解。尽管已有攻击方法被提出,但我们发现现有基于检测的方法存在关键弱点,具体表现为对不现实假设的依赖以及缺乏物理验证。为填补这一空白,我们引入了BadDet+,这是一种基于惩罚的框架,将区域误分类攻击(RMA)和目标消失攻击(ODA)统一起来。核心机制利用对数屏障惩罚来抑制触发输入的真类预测,从而实现(i)位置和尺度不变性,以及(ii)增强的物理鲁棒性。在现实世界基准测试中,BadDet+在合成到物理的转移性能上优于现有RMA和ODA基线,同时保持干净性能。理论分析证实所提出的惩罚作用于特定触发特征子空间内,能够可靠地引发攻击而不影响标准推断。这些结果突显了目标检测中的重大漏洞,并强调了专门防御的必要性。

英文摘要:

Backdoor attacks pose a severe threat to deep learning, yet their impact on object detection remains poorly understood compared to image classification. While attacks have been proposed, we identify critical weaknesses in existing detection-based methods, specifically their reliance on unrealistic assumptions and a lack of physical validation. To bridge this gap, we introduce BadDet+, a penalty-based framework that unifies Region Misclassification Attacks (RMA) and Object Disappearance Attacks (ODA). The core mechanism utilizes a log-barrier penalty to suppress true-class predictions for triggered inputs, resulting in (i) position and scale invariance, and (ii) enhanced physical robustness. On real-world benchmarks, BadDet+ achieves superior synthetic-to-physical transfer compared to existing RMA and ODA baselines while preserving clean performance. Theoretical analysis confirms the proposed penalty acts within a trigger-specific feature subspace, reliably inducing attacks without degrading standard inference. These results highlight significant vulnerabilities in object detection and the necessity for specialized defenses.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑