针对基于Transformer的追踪器，仅用一个边界框生成对抗性扰动实现高效攻击。
Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers
- 基于预测框生成对抗性边界框列表，通过单个框实现白盒攻击。
- 在GOT-10k、UAV123等数据集上超越现有攻击方法，对TransT-M等模型有效。
- 适用于鲁棒性强的Transformer追踪器，适合安全评估与模型防御研究者。
对抗性扰动旨在欺骗神经网络产生错误预测。对于视觉目标追踪器，已有攻击方法通过操纵输出生成扰动。然而，基于Transformer的追踪器会直接预测特定边界框而非候选对象列表，限制了多数现有攻击场景的应用。为解决此问题，我们提出一种新颖的白盒攻击方法，仅需一个边界框即可攻击具有Transformer主干的视觉追踪器。从追踪器预测的边界框出发，生成一组对抗性边界框，并计算这些边界框的对抗损失。实验结果表明，该简单而有效的攻击方法在多个主流基准追踪数据集（如GOT-10k、UAV123、VOT2022STS）上优于现有攻击，对TransT-M、ROMTrack和MixFormer等鲁棒性较强的变压器追踪器均具显著效果。
原文摘要 · Abstract (English)
Adversarial perturbations aim to deceive neural networks into predicting inaccurate results. For visual object trackers, adversarial attacks have been developed to generate perturbations by manipulating the outputs. However, transformer trackers predict a specific bounding box instead of an object candidate list, which limits the applicability of many existing attack scenarios. To address this issue, we present a novel white-box approach to attack visual object trackers with transformer backbones using only one bounding box. From the tracker predicted bounding box, we generate a list of adversarial bounding boxes and compute the adversarial loss for those bounding boxes. Experimental results demonstrate that our simple yet effective attack outperforms existing attacks against several robust transformer trackers, including TransT-M, ROMTrack, and MixFormer, on popular benchmark tracking datasets such as GOT-10k, UAV123, and VOT2022STS.
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。