Trustworthy Machine Learning: Past, Present, and Future

Prof. Somesh Jha
Lubar Professor
Computer Sciences Department
University of Wisconsin, Madison

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.

Speaker’s Bio: 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.

Streamlet: An Absurdly Simple, Textbook Blockchain Protocol

Prof. Elaine Shi
Associate Professor
Computer Science Department
Electrical and Computer Engineering
CyLab Security and Privacy Institute
Carnegie Mellon University, Pittsburgh, PA

Abstract: Numerous works in the past have focused on constructing simple and understandable distributed consensus protocols. In this talk, I will present an absurdly simple consensus protocol called Streamlet. The entire protocol is: every epoch, a leader proposes a block extending the longest chain it has seen so far. Everyone votes for (i.e., signs) the first block proposed by the leader if it extends from one of the longest notarized chains they have seen so far. When a block collects votes from 2/3 of the nodes, it becomes notarized. Notarized does not mean final. Finality is decided with the following rule: for any chain in which all blocks are notarized and moreover, the last three blocks have consecutive epoch numbers, the entire chain except the first block is final.

Streamlet is inspired by the community’s past five years of work on consensus motivated by decentralized blockchains. To the best of our knowledge, it is the simplest embodiment known thus far, and it subsumes classical landmark protocols such as PBFT/Paxos and their numerous variants. It is a great fit for pedagogy. Streamlet has been incorporated into courses at universities such as Stanford and CMU. Streamlet is also part of my new distributed consensus textbook available at This is joint work with Benjamin Chan.

Speaker’s Bio: Elaine Shi is an Associate Professor at Carnegie Mellon University. Her research interests include cryptography, algorithms, distributed systems, foundations of blockchains, and language-based security. She is a recipient of the Packard Fellowship, the Sloan Fellowship, the ONR YIP award, the NSF CAREER award, the NSA Best Scientific Security paper, and various other best-paper and research awards. Elaine obtained her Ph.D. from Carnegie Mellon University, and her bachelor’s degree from Tsinghua University.

Encrypted Databases: Progresses and Challenges

Prof. Kui Ren
Professor and Associate Dean
College of Computer Science and Technology
Zhejiang University, Hangzhou

Abstract: In recent years, we have witnessed an upsurge in cyber-attacks and data breach incidents that put tremendous data at risk, affect millions of users, and cause severe economic losses. As an in-depth defence to counter the persistent and pervasive security threats, maintaining data in always encrypted form is becoming a trend and even a regulatory requirement. Satisfying the demand is particularly challenging in the context of databases, which, as a pillar in modern computing infrastructure, provide indispensable means to organize, store and retrieve data at different scales. The difficulty lies in how to perform the database query processing over encrypted data while meeting the requirements of security, performance, and complex query functions.

This field has grown tremendously over the past two decades, though there is no dominant solution that is universally applicable. Solutions based on cryptographic techniques, e.g., searchable encryption or property-preserving encryption, can efficiently provide certain primitive operations for database queries. But studies have shown that their allowed leakage profiles can be (sometimes highly) exploitable. The recent advent of secure hardware enclaves opens up new opportunities. Yet, the first few enclave-based proposals mostly explore extreme design points that rest on strong assumptions (e.g., huge enclave) or result in weak security (e.g., leaking relations of ciphertexts). In this talk, we will overview these latest advancements and the potential challenges, respectively, and discuss the possible roadmap ahead towards practically more secure, efficient and functional encrypted databases.

Speaker’s Bio: Kui Ren is Professor and Associate Dean of College of Computer Science and Technology at Zhejiang University, where he also directs the Institute of Cyber Science and Technology. Before that, he was SUNY Empire Innovation Professor at State University of New York at Buffalo. He received his PhD degree in Electrical and Computer Engineering from Worcester Polytechnic Institute. Kui’s current research interests include Data Security, IoT Security, AI Security, and Privacy. He received many recognitions including Guohua Distinguished Scholar Award of ZJU, IEEE CISTC Technical Recognition Award, SUNY Chancellor’s Research Excellence Award, Sigma Xi Research Excellence Award, NSF CAREER Award, etc. Kui has published extensively in peer-reviewed journals and conferences and received the Test-of-time Paper Award from IEEE INFOCOM and many Best Paper Awards from IEEE and ACM, including ACM MobiSys, IEEE ICDCS, IEEE ICNP, IEEE Globecom, ACM/IEEE IWQoS, etc. His h-index is 77, with a total citation exceeding 35,000 according to Google Scholar. Kui is a Fellow of ACM and IEEE. He is a frequent reviewer for funding agencies internationally and serves on the editorial boards of many IEEE and ACM journals. Among others, he currently serves as Chair of SIGSAC of ACM China Council, a member of ACM ASIACCS steering committee, and a member of S&T Committee of Ministry of Education of China.