We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
两阶段目标类指引的行人检测对抗补丁生成算法.
- Authors
杨弋鋆; 邵文泽; 邓海松; 葛琦; 李海波
- Abstract
Owing to the vulnerability of deep learning models, attack with adversarial examples has become a pretty hot topic in the past several years at home and abroad. This paper mainly discusses the vulnerability of Yolo-v2, which is a well-known candidate pedestrian detection model for driverless cars. In short, a target-guided two-stage approach is proposed for generating adversarial patches so as to fool Yolo-v2. Specifically speaking, the approach puts forward a new target-guided attack strategy, which enables adversarial patches converge to a definite direction, and successively conducts two stages of adversarial training, which gradually enhances the ability of adversarial patches attacking Yolo-v2. Using Inria as the training set and guided by 79 target classes, it is empirically found that the class "teddy bear" helps the proposed method achieve the best attacking performance. The pedestrian detection IOU of the attacked Yolo-v2 is 0.043 5, which is significantly lower than reference algorithm.
- Subjects
TEDDY bears; DEEP learning; OBJECT recognition (Computer vision); PEDESTRIANS; DRIVERLESS cars
- Publication
Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition), 2022, Vol 34, Issue 4, p565
- ISSN
1673-825X
- Publication type
Article
- DOI
10.3979/j.issn.1673-825X.202012240420