论文标题
变压器编码器检测器模块：使用上下文来改善对象检测的对抗性攻击的鲁棒性
Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection
论文作者
论文摘要
深度神经网络方法表明，对象识别（CNN）和检测（更快的RCNN）任务表现出很高的性能，但是实验表明，这种体系结构容易受到对抗性攻击（FFF，UAP）的影响：低振幅扰动，几乎无法察觉，人眼几乎无法察觉，可以导致降低标签性能。本文提出了一个新的上下文模块，称为\ textIt {变形金刚编码器检测器模块}，可以将其应用于对象检测器以（i）改进对象实例的标签； （ii）提高探测器对对抗攻击的鲁棒性。与基线更快的RCNN检测器相比，所提出的模型可实现较高的地图，F1分数和AUC的平均得分高达13％\％，并且由于从场景中提取的上下文和视觉特征包含了FFF或UAP攻击的图像上，地图得分高出8点，并在模型中添加了上下文和视觉特征。结果表明，简单的临时上下文模块可以显着提高对象检测器的可靠性。
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labeling performance. This article proposes a new context module, called \textit{Transformer-Encoder Detector Module}, that can be applied to an object detector to (i) improve the labeling of object instances; and (ii) improve the detector's robustness to adversarial attacks. The proposed model achieves higher mAP, F1 scores and AUC average score of up to 13\% compared to the baseline Faster-RCNN detector, and an mAP score 8 points higher on images subjected to FFF or UAP attacks due to the inclusion of both contextual and visual features extracted from scene and encoded into the model. The result demonstrates that a simple ad-hoc context module can improve the reliability of object detectors significantly.
