arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.01765cs.CV
收藏

针对鲁棒Transformer跟踪器的对抗攻击可复现性研究

Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers

Université Laval（拉瓦尔大学）；Mila（米拉研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席项目）

Fatemeh Nourilenjan Nokabadi, Jean-François Lalonde, Christian Gagné

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文复现评估了4种对抗攻击对7种目标跟踪器（含3种Transformer架构）的鲁棒性，发现扰动级别变化对攻击效果影响有限，且具备更强交叉注意力建模的Transformer跟踪器展现出更高的对抗鲁棒性。

摘要：

新型Transformer网络已被集成到目标跟踪流程中，并在最新的基准测试中展现出强大的性能。本文旨在理解Transformer跟踪器在对抗攻击下的行为表现，以及不同攻击方法在跟踪数据集上随参数变化的表现。我们进行了一系列实验，以评估现有对抗攻击对基于Transformer和非Transformer骨干网络的目标跟踪器的有效性。我们在7种不同的跟踪器上进行了实验，其中3种基于Transformer，4种采用其他架构。这些跟踪器接受了4种最新攻击方法的测试，以评估它们在VOT2022ST、UAV123和GOT10k数据集上的性能和鲁棒性。我们的实证研究重点评估基于边界框预测与二值掩码预测的目标跟踪器的对抗鲁棒性，以及在不同扰动级别下的攻击方法。有趣的是，我们的研究发现，改变扰动级别可能不会显著影响攻击后的整体目标跟踪结果。类似地，攻击扰动的稀疏性和不可感知性在扰动级别变化时可能保持稳定。通过在所有Transformer跟踪器上应用特定攻击，我们表明具有更强交叉注意力建模能力的新型Transformer跟踪器在VOT2022ST和GOT10k等跟踪数据集上实现了更高的对抗鲁棒性。我们的结果也表明，有必要开发新的攻击方法来有效应对最新类型的Transformer跟踪器。复现本研究所需的代码可在 https://github.com/fatemehN/ReproducibilityStudy 获取。

英文摘要：

New transformer networks have been integrated into object tracking pipelines and have demonstrated strong performance on the latest benchmarks. This paper focuses on understanding how transformer trackers behave under adversarial attacks and how different attacks perform on tracking datasets as their parameters change. We conducted a series of experiments to evaluate the effectiveness of existing adversarial attacks on object trackers with transformer and non-transformer backbones. We experimented on 7 different trackers, including 3 that are transformer-based, and 4 which leverage other architectures. These trackers are tested against 4 recent attack methods to assess their performance and robustness on VOT2022ST, UAV123 and GOT10k datasets. Our empirical study focuses on evaluating adversarial robustness of object trackers based on bounding box versus binary mask predictions, and attack methods at different levels of perturbations. Interestingly, our study found that altering the perturbation level may not significantly affect the overall object tracking results after the attack. Similarly, the sparsity and imperceptibility of the attack perturbations may remain stable against perturbation level shifts. By applying a specific attack on all transformer trackers, we show that new transformer trackers having a stronger cross-attention modeling achieve a greater adversarial robustness on tracking datasets, such as VOT2022ST and GOT10k. Our results also indicate the necessity for new attack methods to effectively tackle the latest types of transformer trackers. The codes necessary to reproduce this study are available at https://github.com/fatemehN/ReproducibilityStudy.

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。

↑