Practical GAN-based Synthetic IP Header Trace Generation Using NetShare


We explore the feasibility of using Generative Adversarial Networks (GANs) to automatically learn generative models to generate synthetic packet- and flow header traces for network-ing tasks (e.g., telemetry, anomaly detection, provisioning). We identify key fidelity, scalability, and privacy challenges and tradeoffs in existing GAN-based approaches. By synthesizing domain-specific insights with recent advances in machine learning and privacy, we identify design choices to tackle these challenges. Building on these insights, we develop an end-to-end framework, NetShare. We evaluate NetShare on six diverse packet header traces and find that: (1) across distributional metrics and traces, it achieves 46% more accuracy than baselines, and (2) it meets users’ requirements of downstream tasks in evaluating accuracy and rank ordering of candidate approaches.

The Speaker

Vyas Sekar is the Tan Family Professor of Electrical and Computer Engineering in the Electrical and Computer Engineering Department at CMU. His work is broadly at the intersection of networks, systems, and security. His work has been recognized with numerous awards including the NSF CAREER Award, SIGCOMM Rising Star Award, NSA Science of Security prize, the IRTF Applied Networking Research Prize, the SIGCOMM Test of Time Award, and the Intel Outstanding Researcher Award. He was most recently the founding co-director of the IoT@Cylab initiative and is a founding co-director of the Future of Enterprise Security Initiative at Cylab.