1. 이성윤 교수 (한양대학교 소프트웨어학부) 강연시간 : 17:00-17:45

강연제목 : Survival of the Fittest in Deep Learning: SGD and Implicit Interaction Regularization

 

강연소개내용 : Over the decades, SGD has been able to “survive” in the competitive and wild “nature” of learning

algorithms. But how? How could this algorithm have been “selected” by the practitioners? In this

talk, we try to answer this question.

 

 

 

 

2. 한준 교수(연세대학교 전자과) 강연시간 : 17:55-18:35

강연제목 : Benefits and Risks of Sensing for Cyber-Physical Security

 

강연소개내용(Abstract) : With the emergence of the Internet-of-Things (IoT) and Cyber-Physical Systems (CPS), we are witnessing a wealth of exciting applications that enable computational devices to interact with the physical world via an overwhelming number of sensors and actuators. However, such interactions pose new challenges to traditional approaches of security and privacy. In this talk, I will present how I utilize sensor data to provide security and privacy protections for IoT/CPS scenarios, and further introduce novel security threats arising from similar sensor data. Specifically, I will highlight some of our recent projects that leverage sensor data for attack and defense in various IoT applications. I will also introduce my future research directions such as identifying and defending against unforeseen security challenges from newer application domains including smart homes, buildings, and vehicles.