Speaker:
Yimin Chen
Virginia Tech

Abstract:

In this talk, we explore security and privacy related to meta-learning, a learning paradigm aiming to learn 'cross-task' knowledge instead of 'single-task' knowledge. For privacy perspective, we conjecture that meta-learning plays an important role in future federated learning and look into federated meta-learning systems with differential privacy design for task privacy protection. For security perspective, we explore anomaly detection for machine learning models. Particularly, we explore poisoning attacks on machine learning models in which poisoning training samples are the anomaly. Inspired from that poisoning samples degrade trained models through overfitting, we exploit meta-training to counteract overfitting, thus enhancing model robustness.

About: Yimin Chen is now a postdoctoral researcher in Computer Science department in Virginia Tech. Currently his research mainly focuses on differential privacy, anomaly detection, adversarial example, and private learning. Before he worked on security and privacy of mobile computing systems for his PhD study. He obtained a PhD degree from Arizona State University in 2018, a MPhil degree from Chinese University of Hong Kong in 2013, and a BS degree from Peking University in 2010.

The weekly security seminar has been held every semester since spring of 1992. We invite personnel at Purdue and visitors from outside to present on topics of particular interest to them in the areas of computer and network security, computer crime investigation, information warfare, information ethics, public policy for computing and security, the computing "underground," and other related topics. More info