Skip to content

Latest commit

 

History

History
105 lines (81 loc) · 3.69 KB

phys_attacks.md

File metadata and controls

105 lines (81 loc) · 3.69 KB

Physical-World Adversarial Attacks

Here're some resources about Physical-World Adversarial Attacks

Intros:

  • Physical-world adversarial attacks involve manipulating real-world objects to deceive AVs. For instance, subtly altering road signs so that they’re misinterpreted by an AV’s vision system, causing incorrect or dangerous actions.

Physically Realizable Targeted Adversarial Attacks on Autonomous Driving [READ]

paper link: here

citation:

@phdthesis{buddareddygari2021physically,
  title={Physically Realizable Targeted Adversarial Attacks on Autonomous Driving},
  author={Buddareddygari, Prasanth},
  year={2021},
  school={Arizona State University}
}

Dirty road can attack: Security of deep learning based automated lane centering under {Physical-World} attack [READ]

paper link: here

citation:

@inproceedings{sato2021dirty,
  title={Dirty road can attack: Security of deep learning based automated lane centering under $\{$Physical-World$\}$ attack},
  author={Sato, Takami and Shen, Junjie and Wang, Ningfei and Jia, Yunhan and Lin, Xue and Chen, Qi Alfred},
  booktitle={30th USENIX Security Symposium (USENIX Security 21)},
  pages={3309--3326},
  year={2021}
}

Invisible for both camera and lidar: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks [READ]

paper link: here

citation:

@inproceedings{cao2021invisible,
  title={Invisible for both camera and lidar: Security of multi-sensor fusion based perception in autonomous driving under physical-world attacks},
  author={Cao, Yulong and Wang, Ningfei and Xiao, Chaowei and Yang, Dawei and Fang, Jin and Yang, Ruigang and Chen, Qi Alfred and Liu, Mingyan and Li, Bo},
  booktitle={2021 IEEE Symposium on Security and Privacy (SP)},
  pages={176--194},
  year={2021},
  organization={IEEE}
}

Multi-source adversarial sample attack on autonomous vehicles [UNREAD]

paper link: here

citation:

@article{xiong2021multi,
  title={Multi-source adversarial sample attack on autonomous vehicles},
  author={Xiong, Zuobin and Xu, Honghui and Li, Wei and Cai, Zhipeng},
  journal={IEEE Transactions on Vehicular Technology},
  volume={70},
  number={3},
  pages={2822--2835},
  year={2021},
  publisher={IEEE}
}

Physgan: Generating physical-world-resilient adversarial examples for autonomous driving [READ]

paper link: here

citation:

@inproceedings{kong2020physgan,
  title={Physgan: Generating physical-world-resilient adversarial examples for autonomous driving},
  author={Kong, Zelun and Guo, Junfeng and Li, Ang and Liu, Cong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={14254--14263},
  year={2020}
}

Simple physical adversarial examples against end-to-end autonomous driving models [UNREAD]

paper link: here

citation:

@inproceedings{boloor2019simple,
  title={Simple physical adversarial examples against end-to-end autonomous driving models},
  author={Boloor, Adith and He, Xin and Gill, Christopher and Vorobeychik, Yevgeniy and Zhang, Xuan},
  booktitle={2019 IEEE International Conference on Embedded Software and Systems (ICESS)},
  pages={1--7},
  year={2019},
  organization={IEEE}
}