针对视频目标检测设计低可见度结构化对抗攻击
Structured Universal Adversarial Attacks on Object Detection for Video Sequences
- 用核范数正则化让扰动集中在背景区域，减少视觉畸变
- 在COCO-Vid和YouTube-VIS数据集上成功率超90%，隐蔽性更强
- 适合研究模型鲁棒性或防御机制的开发者参考
基于视频的目标检测在安全关键应用中至关重要。尽管深度学习检测器表现优异，仍易受通用扰动攻击影响。本文提出一种最小畸变的通用对抗攻击方法，利用核范数正则化使扰动集中于背景区域。通过自适应优化的指数梯度法高效求解，提升可扩展性与收敛速度。实验表明，该方法在COCO-Vid和YouTube-VIS数据集上均优于低秩投影梯度下降与Frank-Wolfe基攻击，在攻击效果与隐蔽性间取得更好平衡。代码与数据已公开于https://github.com/jsve96/AO-Exp-Attack。
原文摘要 · Abstract (English)
Video-based object detection plays a vital role in safety-critical applications. While deep learning-based object detectors have achieved impressive performance, they remain vulnerable to adversarial attacks, particularly those involving universal perturbations. In this work, we propose a minimally distorted universal adversarial attack tailored for video object detection, which leverages nuclear norm regularization to promote structured perturbations concentrated in the background. To optimize this formulation efficiently, we employ an adaptive, optimistic exponentiated gradient method that enhances both scalability and convergence. Our results demonstrate that the proposed attack outperforms both low-rank projected gradient descent and Frank-Wolfe based attacks in effectiveness while maintaining high stealthiness. All code and data are publicly available at https://github.com/jsve96/AO-Exp-Attack.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。