Tsinghua University won the Distinguished Paper Award at the 32nd USENIX Security Symposium, one of the most prestigious academic conferences in the field of information security. The paper, titled “An Efficient Design of Intelligent Network Data Plane”, was co-authored by Guangmeng Zhou, Zhuotao Liu, Chuanpu Fu, Qi Li, and Ke Xu of the Department of Computer Science and Technology and the Institute for Network Sciences and Cyberspace at Tsinghua University. This is the first time that Chinese research institutions and scholars have won this award independently. As a result, Tsinghua University has become the leading domestic scientific research institution in terms of the number of award-winning papers in the four flagship academic conferences in the field of cybersecurity, and is also among the best in the world.
The paper introduces a new paradigm for jointly designing and deploying intelligent AI models and programmable network hardware, which can support a variety of tasks, such as network malicious traffic detection, secure routing, and network performance optimization. The paper first formally defines the Intelligent Network Data Plane (INDP), and builds an integrated software and hardware system that enables AI-powered network traffic processing and forwarding at line-speed. The paper's anonymous reviewers, who were randomly selected from a world-class program committee specializing in cybersecurity, collectively believe that the deployment of AI models on network hardware devices has both important scientific significance and foreseeable engineering impact.
The USENIX Security Symposium is an annual conference that has been held since the early 1990s. It is considered one of the most prestigious conferences in the field of information security. The China Computer Federation recognizes the USENIX Security Symposium as a Class A international academic conference on information security. The 32nd USENIX Security Symposium was held in California, USA from August 9th to 11th, 2023.