Abstract:
Big data powered machine learning has enjoyed a remarkable success in a broad area of applications, ranging from speech recognition, computer vision, machine translations, to software bug localization, manufacture defect detection, medical diagnosis, market analysis, and so forth. As data-driven machine learning frameworks and algorithms are increasingly being used to make decisions for people and about people, such as Amazon Go for checkout-free shopping, Uber self-driving cars, Apple Siri intelligent personal assistant, we foresee two opposite ends of the spectrum: On one hand, the use of algorithmic decision making will provide people with life-enriching experiences, convenience, and opportunities, and on the other hand, the use of algorithmic decision making will also open doors for potential misuse and abuse, including intentional and unfair biases or malicious intentions. Furthermore, with a growing number of open source machine learning software frameworks publically available, supervise or unsupervised learning are being widely deployed in a wide range of machine learning applications. This lecture will show with illustrative examples that without an in-depth understanding of the ways in which algorithms learn, make inference and reach decision, one can easily deceive these machine intelligent learning systems to misbehave, challenging the trust, security and privacy of machine learning systems, services and applications. I will also outline some cool projects on security, privacy and trust of artificial intelligence and machine learning security systems and applications.
Personal introduction:
Prof. Dr. Ling Liu is a Professor in the School of Computer Science at Georgia Institute of Technology. She directs the research programs in Distributed Data Intensive Systems Lab (DiSL), examining various aspects of large-scale data intensive systems. Prof. Liu is an internationally recognized expert in the areas of Big Data Systems and Analytics, Distributed Systems, Database and Storage Systems, Internet Computing, Privacy, Security and Trust. Prof. Liu has published over 300 international journal and conference articles, and is a recipient of the best paper award from a number of top venues, including ICDCS, WWW, Pat Goldberg Memorial Best Paper Award, IEEE CLOUD, IEEE ICWS, ACM/IEEE CCGrid 2015, IEEE Edge. Prof. Liu is an elected IEEE Fellow and a recipient of IEEE Computer Society Technical Achievement Award. Prof. Liu has served as the editor in chief of IEEE Transactions on Services Computing from 2013-2016, the program chairs of numerous IEEE and ACM conferences in the fields of big data, cloud computing, data engineering, distributed computing, very large databases, including the co-PC chair of The Web 2019 (WWW 2019). Currently, Prof. Liu is serving as the Editor in Chief of ACM Transactions on Internet Technology (TOIT). Prof. Liu’s research is primarily sponsored by NSF, IBM and Intel.