敵対的検出:物体検出モデルへのリアルタイム攻撃
Adversarial Detection: Attacking Object Detection in Real Time
物体検出モデルに対する初のリアルタイムオンライン攻撃を提案し、存在しない物体のバウンディングボックスを約20回の反復で約90%の成功率で生成できることを示した。
著者: Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom
分類: cs.AI, cs.CV, cs.RO
原文アブストラクト
Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.
