Keynote Speakers



Title: Situation Knowledge on Demand (SKOD)

The objective of this research is to fuse streaming data from multiple sources and identify rare events to alert the user and meet the mission requirements. The user can ask for specific information or the machine learning system will learn the needs/interest of user and forward new incoming data with a relevance score. Research questions such as trustworthiness of data, variation of data values from same source (such as sensor, video camera, user tweet, police incident report) are addressed due to uncertainty of data accuracy and noise.
Extracting relevant patterns from heterogeneous data streams poses significant computational and analytical challenges. Identifying such patterns and pushing corresponding content to interested users according to mission needs in real-time is the challenge. This research utilizes the best in Database systems, Knowledge representation, Machine Learning to get the right data to the right user at the right time with completeness and low noise. If user’s need is unmet, queries evolve and get modified to come close to satisfy mission needs which may themselves be unclear. If need is partially met, when new streaming data streams in, this research connects relevant data to queries. The knowledge for further processing is kept in the form of queries (megabytes) vs database (giga bytes). Application of this research are to assist in security at military bases and the “missing person” problem. When a suspect or a person is missing, police want to find him/her. The same problem arises in amber alerts, prison escapes, and missing children. When an incident report or 911 call arrives in police station, a physical description of the missing person (e.g., white male with medium built wearing a blue shirt, and black jeans) is available. Families may give additional details of a missing child. Information such as specific medical conditions such as autism spectrum disorder or clinical depression may be available. This research is also improving the interaction of police when they deal with a person with mental issues.
The research leads to a scalable, real-time, fault-tolerant, privacy preserving architecture that consumes streams of multimodal data (e.g., video, text, sound) utilizing publish/subscribe stream engines and RDBMS microservices. We utilize neural networks to extract relevant objects from video and latent semantic indexing techniques to model topics for unstructured text. We presents a unique Situational Knowledge Query Engine that continuously builds a multimodal relational knowledge base constructed using SQL queries and pushes dynamic content to relevant users through triggers based on modeling of users’ interests. We analyze an extensive collection of Cambridge data (millions of Twitter tweets, 35+ structured datasets, and 100+ hours of video traffic, and needs for police, public works and citizens). At present data from West Lafayette police is being analyzed to provide identifying suspicious activity and deal with disasters such as school shooting. We continue to learn and collaborate with our sponsor Northrup Grumman researchers to demonstrate the feasibility of the proof-of-concept.

It is the joint work on NGC-REALM-Consortium with Mike Stonebreaker (MIT) and Matei Zaharia (Stanford)




Click here for profile


Title: Trustworthy Machine Learning: Past, Present, and Future

Abstract: Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms, especially deep neural networks (DNNs), are being used in diverse domains where trustworthiness is a concern, including automotive systems, finance, healthcare, natural language processing, and malware detection. Of particular concern is the use of ML algorithms in cyber-physical systems (CPS), such as self-driving cars and aviation, where an adversary can cause serious consequences. Interest in this area of research has simply exploded. In this work, we will cover the state-of-the-art in trustworthy machine learning, and then cover some interesting future trends.



Biography: Somesh Jha received his B.Tech from Indian Institute of Technology, New Delhi in Electrical Engineering. He received his Ph.D. in Computer Science from Carnegie Mellon University under the supervision of Prof. Edmund Clarke (a Turing award winner). Currently, Somesh Jha is the Lubar Professor in the Computer Sciences Department at the University of Wisconsin (Madison). His work focuses on analysis of security protocols, survivability analysis, intrusion detection, formal methods for security, and analyzing malicious code. Recently, he has focussed his interested on privacy and adversarial ML (AML). Somesh Jha has published several articles in highly-refereed conferences and prominent journals. He has won numerous best-paper and distinguished-paper awards. Prof Jha also received the NSF career award. Prof. Jha is the fellow of the ACM and IEEE.




Click here for profile


Title: From artifacts to systems to people: evolving directions in computing research and education

Computing is now “old enough” as a discipline that we can already detect broad trends in research directions. We discuss these trends, with an emphasis on both current and future directions in computing research, which we see reflected locally (at my own university, UMass Amherst) nationally and internationally. We’ll discuss recent national computing research and education programmatics and trends in the US, and the role of computing in the larger R&D enterprise.



Jim Kurose is a Distinguished University Professor of Computer Science and Associate Chancellor for Partnerships and Innovation at the University of Massachusetts, where he has been on the faculty since receiving his PhD in computer science from Columbia University. He has held visiting scientist positions at IBM Research, Technicolor, INRIA and the Sorbonne University. His research interests include computer network architecture and protocols, network measurement, sensor networks, and multimedia communication. From 2015 to 2019, Jim served as Assistant Director at the US National Science Foundation, where he led the Directorate of Computer and Information Science and Engineering, and in 2018 served as the Assistant Director for Artificial Intelligence in the White House Office of Science and Technology Policy. He received the IEEE Infocom Award, ACM SIGCOMM Lifetime Achievement Award, ACM Sigcomm Test of Time Award, and IEEE/CS Taylor Booth Education Medal. He is a member of the National Academy of Engineering, and a Fellow of the ACM and IEEE. With Keith Ross, he is the co-author of the best-selling textbook, Computer Networking: a Top Down Approach (Pearson), now in its 8th edition.

Click here for profile


Title: Cloud, Fog, Edge Computing for Industrial Internet of Things

The keynote deals with Cloud continuum and its employment for innovation in manufacturing, also motivated by the fact that in our area many companies work both in manufacturing and automotive. We start from the main distinctions within Cloud continuum, from Cloud (multicloud). Fog, and Egde to support new interactions toward Industrial IoT or Industry 4.0. We show several examples of potential innovative solutions, integrating also NFV, containerization, and crowd sensing stressing the architecture support solutions. A short illustration of a local Competence Center Bi-REX is described. Finally, some evolutions an future trends are illustrated.



Antonio Corradi is with the University of Bologna as a full professor of computer engineering, in the area of Distributed Systems and Computer Networks since 2000. His research interests span from middleware for pervasive and heterogeneous computing, from multi cloud solutions to IoT, Fog, and Edge, from innovation services for smart cities to manufacturing innovation design, from pub/sub QoS supports to optimized RDMA access, from new serverless architectures and FaaS to crowdsourcing for evolved sensors, from performance evaluation to system monitoring and management. He has always given basic and advanced courses in all above areas also for IT professional to build a solid view of computing infrastructures. He has also intervened for the Universities of Bologna in many areas, such as in internationalization of the University of Bologna, by serving as the Department chair since few months ago, in promoting new connections and relationship with European and worldwide organizations. In the last decades, he is deep involved in new innovation initiatives in public engagement. and also moved his research into service integration and technology transfer in the area of innovation, becoming president of the CLUST-ER ‘Innovation in Services’. Antonio is part of IEEE and ACM, and is active in publishing more than 350 contributions in journal, magazines and international conferences.

Click here for profile


Title: Robust, Fair, and Privacy Preserving Deep Learning

Abstract: Modern machine learning and computer vision algorithms have demonstrated superlative performances in various applications and have been utilized in real world scenarios. Despite the enhanced performance, robustness of these algorithms against attacks, privacy leaks, and fairness/bias are major concerns. This talk will give an overview of “trustworthiness" aspects of building ML and CV systems. We will discuss different types of attacks such as digital adversarial attacks, and morphing/tampering using GANs. We will also discuss the effect of bias on ML models and showcase that different factors affect the performance of modern algorithms. Finally, we will also discuss privacy preserving aspects of modern CV and ML algorithms.



Biography: Mayank Vatsa received the M.S. and Ph.D. degrees in Computer Science from West Virginia University, USA, in 2005 and 2008, respectively. He is currently a Professor with IIT Jodhpur, India, and the Project Director of the TIH on Computer Vision and Augmented & Virtual Reality under the NM-ICPS (Government of India). He is also an Adjunct Professor with IIIT-Delhi, India and West Virginia University, USA. His areas of interest are machine learning, computer vision, and biometrics. He has co-edited books on Deep learning in Biometrics and Domain Adaptation for Visual Understanding. He is the recipient of the prestigious Swarnajayanti Fellowship from the Government of India, the A. R. Krishnaswamy Faculty Research Fellowship at the IIIT-Delhi, and several best paper and best poster awards at international conferences. He is an Associate Editor of Pattern Recognition, the General Co-Chair of IJCB 2020, and the PC Co-Chair of IEEE FG2021. He has also served as the Vice President (Publications) of the IEEE Biometrics Council where he started the IEEE Transactions on Biometrics, Behavior, And Identity Science.

Click here for profile