Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection
This work provides an incremental improvement in robustness to adversarial attacks for object detection, which is important for safety-critical applications.
This paper addresses the vulnerability of object detectors to adversarial attacks by proposing a Transformer-Encoder Detector Module. The module improves labeling performance and robustness, achieving up to 13% higher mAP, F1, and AUC scores compared to Faster-RCNN, and an 8-point mAP increase on images with FFF or UAP attacks.
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.