检测Transformer的对抗鲁棒性评估
Evaluating the Adversarial Robustness of Detection Transformers
AI总结：
本文系统评估了DETR及其变体在白盒与黑盒对抗攻击下的脆弱性，发现其易受攻击且变体间迁移性高，并提出一种利用中间损失的新型无目标攻击，为提升Transformer检测器的鲁棒性提供依据。
摘要：
鲁棒的目标检测对于自动驾驶和移动机器人至关重要，其中对车辆、行人和障碍物的准确检测是确保安全的基础。尽管目标检测Transformer（DETR）取得了显著进展，但其对对抗攻击的鲁棒性仍未得到充分探索。本文使用MS-COCO和KITTI数据集，在通用场景和自动驾驶场景下，对DETR模型及其变体在白盒和黑盒对抗攻击下的表现进行了全面评估。我们扩展了主流的白盒攻击方法（FGSM、PGD和CW）来评估DETR的脆弱性，结果表明DETR模型与传统的基于CNN的检测器类似，对对抗攻击高度敏感。我们广泛的迁移性分析揭示，DETR变体之间存在较高的网络内迁移性，但向基于CNN模型的跨网络迁移性有限。此外，我们提出了一种专门针对DETR设计的新型无目标攻击，利用其中间损失函数以最小的扰动诱导错误分类。自注意力特征图的可视化提供了对抗攻击如何影响DETR模型内部表示的见解。这些发现揭示了检测Transformer在标准对抗攻击下的关键脆弱性，强调了未来研究需要增强基于Transformer的目标检测器在安全关键应用中的鲁棒性。
英文摘要：
Robust object detection is critical for autonomous driving and mobile robotics, where accurate detection of vehicles, pedestrians, and obstacles is essential for ensuring safety. Despite the advancements in object detection transformers (DETRs), their robustness against adversarial attacks remains underexplored. This paper presents a comprehensive evaluation of DETR model and its variants under both white-box and black-box adversarial attacks, using the MS-COCO and KITTI datasets to cover general and autonomous driving scenarios. We extend prominent white-box attack methods (FGSM, PGD, and CW) to assess DETR vulnerability, demonstrating that DETR models are significantly susceptible to adversarial attacks, similar to traditional CNN-based detectors. Our extensive transferability analysis reveals high intra-network transferability among DETR variants, but limited cross-network transferability to CNN-based models. Additionally, we propose a novel untargeted attack designed specifically for DETR, exploiting its intermediate loss functions to induce misclassification with minimal perturbations. Visualizations of self-attention feature maps provide insights into how adversarial attacks affect the internal representations of DETR models. These findings reveal critical vulnerabilities in detection transformers under standard adversarial attacks, emphasizing the need for future research to enhance the robustness of transformer-based object detectors in safety-critical applications.
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。
