The rapid development of artificial intelligence, especially deep learning technology, has advanced autonomous driving systems . However, the safety and security of deep learning-based autonomousdriving are severely challenged by these attacks . This survey provides a thorough analysis of different attacksthat may jeopardize ADSs, as well as the corresponding state-of-the-art defensemechanisms . The analysis is unrolled by taking an in-depth overview of eachstep in the ADS workflow, covering adversarial attacks for various deeplearning models and attacks in both physical and cyber context . Furthermore, some promising research directions are suggested in order to improve deeplearning-based safety, including model robustness training, model testing and verification, and anomaly detection based on cloud/edgeservers. Furthermore,some promising research

Author(s) : Yao Deng, Tiehua Zhang, Guannan Lou, Xi Zheng, Jiong Jin, Qing-Long Han

Links : PDF - Abstract

Code :

Keywords : attacks - based - deep - learning - deeplearning -

Leave a Reply

Your email address will not be published. Required fields are marked *