2022-09-11 更新
On the Transferability of Adversarial Examples between Encrypted Models
Authors:Miki Tanaka, Isao Echizen, Hitoshi Kiya
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, namely, AEs generated for a source model fool other (target) models. In this paper, we investigate the transferability of models encrypted for adversarially robust defense for the first time. To objectively verify the property of transferability, the robustness of models is evaluated by using a benchmark attack method, called AutoAttack. In an image-classification experiment, the use of encrypted models is confirmed not only to be robust against AEs but to also reduce the influence of AEs in terms of the transferability of models.
PDF to be appear in ISPACS 2022
点此查看论文截图
Adversarial Detection: Attacking Object Detection in Real Time
Authors:Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom
Intelligent robots hinge on accurate object detection models to perceive the environment. Advances in deep learning security unveil that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. It is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. There is still a gap between theoretical discoveries and real-world applications. We bridge the gap by proposing the first real-time online attack against object detection models. We devised three attacks that fabricate bounding boxes for nonexistent objects at desired locations.
PDF 7 pages, 10 figures
点此查看论文截图