Biblio

Filters: Author is Li, Mohan  [Clear All Filters]
2023-01-06
Fan, Jiaxin, Yan, Qi, Li, Mohan, Qu, Guanqun, Xiao, Yang.  2022.  A Survey on Data Poisoning Attacks and Defenses. 2022 7th IEEE International Conference on Data Science in Cyberspace (DSC). :48—55.
With the widespread deployment of data-driven services, the demand for data volumes continues to grow. At present, many applications lack reliable human supervision in the process of data collection, which makes the collected data contain low-quality data or even malicious data. This low-quality or malicious data make AI systems potentially face much security challenges. One of the main security threats in the training phase of machine learning is data poisoning attacks, which compromise model integrity by contaminating training data to make the resulting model skewed or unusable. This paper reviews the relevant researches on data poisoning attacks in various task environments: first, the classification of attacks is summarized, then the defense methods of data poisoning attacks are sorted out, and finally, the possible research directions in the prospect.
2018-09-28
Han, Meng, Li, Lei, Peng, Xiaoqing, Hong, Zhen, Li, Mohan.  2017.  Information Privacy of Cyber Transportation System: Opportunities and Challenges. Proceedings of the 6th Annual Conference on Research in Information Technology. :23–28.
The Cyber Transport Systems (CTSs) have made significant advancement along with the development of the information technology and transportation industries worldwide. The rapid proliferation of cyber transportation technology provides rich information and infinite possibilities for our society to understand and use the complex inherent mechanism, which governs the novel intelligence world. In addition, applying information technology to cyber transportation applications open a range of new application scenarios, such as vehicular safety, energy efficiency, reduced pollution, and intelligent maintenance services. However, while enjoying the services and convenience provided by CTS, users, vehicles, even the systems might lose privacy during information transmitting and processing. This paper summarizes the state-of-art research findings on information privacy issues in a broad range. We firstly introduce the typical types of information and the basic mechanisms of information communication in CTS. Secondly, considering the information privacy issues of CTS, we present the literature on information privacy issues and privacy protection approaches in CTS. Thirdly, we discuss the emerging challenges and the opportunities for the information technology community in CTS.