Attacking Point Cloud Segmentation with Color-only Perturbation

no code implementations • 11 Dec 2021 • Jiacen Xu, Zhe Zhou, Boyuan Feng Yufeng Ding, Zhou Li

Recent research efforts on 3D point-cloud semantic segmentation have achieved outstanding performance by adopting deep CNN (convolutional neural networks) and GCN (graph convolutional networks).

Autonomous Driving Object Recognition +2

Continuous Release of Data Streams under both Centralized and Local Differential Privacy

no code implementations • 24 May 2020 • Tianhao Wang, Joann Qiongna Chen, Zhikun Zhang, Dong Su, Yueqiang Cheng, Zhou Li, Ninghui Li, Somesh Jha

To our knowledge, this is the first LDP algorithm for publishing streaming data.

Your Smart Home Can't Keep a Secret: Towards Automated Fingerprinting of IoT Traffic with Neural Networks

no code implementations • 31 Aug 2019 • Shuaike Dong, Zhou Li, Di Tang, Jiongyi Chen, Menghan Sun, Kehuan Zhang

However, in the meantime, such a fast-growing technology has also introduced new privacy issues, which need to be better understood and measured.

Cryptography and Security

Understanding Android Obfuscation Techniques: A Large-Scale Investigation in the Wild

no code implementations • 5 Jan 2018 • Shuaike Dong, Menghao Li, Wenrui Diao, Xiangyu Liu, Jian Liu, Zhou Li, Fenghao Xu, Kai Chen, Xiao-Feng Wang, Kehuan Zhang

In this paper, we seek to better understand Android obfuscation and depict a holistic view of the usage of obfuscation through a large-scale investigation in the wild.

Cryptography and Security