Select a calendar:
Filter November Events by Event Type:
Events for the 3rd week of November
-
Fall 2018 Joint CSC@USC/CommNetS-MHI Seminar Series
Mon, Nov 12, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Munther Dahleh, MIT
Talk Title: A Marketplace for Data: An Algorithmic Solution
Abstract: In this work, we aim to create a data marketplace; a robust real-time matching mechanism to efficiently buy and sell training data for Machine Learning tasks. While the monetization of data and pre-trained models is an essential focus of industry today, there does not exist a market mechanism to price training data and match buyers to vendors while still addressing the associated (computational and other) complexity. The challenge in creating such a market stems from the very nature of data as an asset: it is freely replicable; its value is inherently combinatorial due to correlation with signal in other data; prediction tasks and the value of accuracy vary widely; usefulness of training data is difficult to verify a priori without first applying it to a prediction task. As our main contributions we: propose a mathematical model for a two-sided data market and formally define the key associated challenges; construct algorithms for such a market to function and rigorously prove how they meet the challenges defined. We highlight two technical contributions: a new notion of fairness required for cooperative games with freely replicable goods; a truthful, zero regret mechanism for auctioning a particular class of combinatorial goods based on utilizing Myerson's payment function and the Multiplicative Weights algorithm. These might be of independent interest.
This is a joint work with Anish Agarwal, Tuhin Sarkar, and Devavrat Shah.
Biography: Munther A. Dahleh received his PhD degree from Rice University, Houston, TX, in 1987 in Electrical and Computer Engineering. Since then, he has been with the Department of Electrical Engineering and Computer Science (EECS), MIT, Cambridge, MA, where he is now the William A. Coolidge Professor of EECS. He is also a faculty affiliate of the Sloan School of Management. He is the founding director of the newly formed MIT Institute for Data, Systems, and Society (IDSS). Previously, he held the positions of Associate Department Head of EECS, Acting Director of the Engineering Systems Division, and Acting Director of the Laboratory for Information and Decision Systems. He was a visiting Professor at the Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, for the Spring of 1993. He has consulted for various national research laboratories and companies. Dr. Dahleh is interested in Networked Systems with applications to Social and Economic Networks, financial networks, Transportation Networks, Neural Networks, and the Power Grid. Specifically, he focuses on the development of foundational theory necessary to understand, monitor, and control systemic risk in interconnected systems. His work draws from various fields including game theory, optimal control, distributed optimization, information theory, and distributed learning. His collaborations include faculty from all five schools at MIT. Dr. Dahleh is the co-author (with Ignacio Diaz-Bobillo) of the book Control of Uncertain Systems: A Linear Programming Approach, published by Prentice-Hall, and the co-author (with Nicola Elia) of the book Computational Methods for Controller Design, published by Springer. He is four-time recipient of the George Axelby outstanding paper award for best paper in IEEE Transactions on Automatic Control. He is also the recipient of the Donald P. Eckman award from the American Control Council in 1993 for the best control engineer under 35. He is a fellow of IEEE and IFAC. He has given many keynote lectures at major conferences.
Host: Ketan Savla, ksavla@usc.edu
More Info: http://csc.usc.edu/seminars/2018Fall/dahleh.html
More Information: 18.11.12_Dahleh_MIT-CSC Seminar.pdf
Location: 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
Event Link: http://csc.usc.edu/seminars/2018Fall/dahleh.html
-
Trusted Inference Engine: Preventing Neural Network Exfiltration in Hardware Devices
Tue, Nov 13, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Michel A. Kinsy, Boston University
Talk Title: Trusted Inference Engine: Preventing Neural Network Exfiltration in Hardware Devices
Abstract: Companies, in their push to incorporate artificial intelligence - in particular, machine learning - into their Internet of Things (IoT), system-on-chip (SoC), and automotive applications, will have to address a number of design challenges related to the secure deployment of artificial intelligence learning models and techniques. Machine learning (ML) models are often trained using private datasets that are very expensive to collect, or highly sensitive, using large amounts of computing power. The models are commonly exposed either through online APIs, or used in hardware devices deployed in the field or given to the end users. This gives incentives to adversaries to attempt to steal these ML models as a proxy for gathering datasets. While API-based model exfiltration has been studied before, the theft and protection of machine learning models on hardware devices have not been explored as of now. In this work, we examine this important aspect of the design and deployment of ML models. We illustrate how an attacker may acquire either the model or the model architecture through memory probing, side-channels, or crafted input attacks, and propose power-efficient obfuscation as an alternative to encryption, and timing side-channel countermeasures.
Biography: Michel A. Kinsy is an Assistant Professor in the Department of Electrical and Computer Engineering at Boston University (BU), where he directs the Adaptive and Secure Computing Systems (ASCS) Laboratory. He focuses his research on computer architecture, hardware-level security, neural network accelerator designs, and cyber-physical systems. Dr. Kinsy is an MIT Presidential Fellow, the 2018 MWSCAS Myril B. Reed Best Paper Award Recipient, DFT'17 Best Paper Award Finalist, and FPL'11 Tools and Open-Source Community Service Award Recipient. He earned his PhD in Electrical Engineering and Computer Science in 2013 from the Massachusetts Institute of Technology. His doctoral work in algorithms to emulate and control large-scale power systems at the microsecond resolution inspired further research by the MIT spin-off Typhoon HIL, Inc. Before joining the BU faculty, Dr. Kinsy was an assistant professor in the Department of Computer and Information Systems at the University of Oregon, where he directed the Computer Architecture and Embedded Systems (CAES) Laboratory. From 2013 to 2014, he was a Member of the Technical Staff at the MIT Lincoln Laboratory.
Host: Xuehai Qian, xuehai.qian@usc.edu
More Information: 18.11.13 Michel Kinsy_CENG Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
-
Intermittent Computing Systems
Fri, Nov 16, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Brandon Lucia, Carnegie Mellon University
Talk Title: Intermittent Computing Systems
Abstract: The emergence of extremely low-power computing components and efficient energy-harvesting power systems has led to the creation of computer systems that operate using tiny amounts of energy scavenged from their environment. These devices create opportunities for systems where batteries and tethered power are inapplicable: sensors deeply embedded in pervasive civil infrastructure, in-body health monitors, and devices in extreme environments like glaciers, volcanoes, and space. The key challenge is that these devices operate only intermittently, as energy is available, requiring both hardware and software to tolerate power failures that may happen hundreds of times per second. This talk will describe the landscape of intermittent computing systems. I will focus on new programming and execution models that are robust to arbitrarily frequent power failures. In particular, the talk will focus on three models, DINO, Chain, and Alpaca, which we developed as a progression toward a system that is simple to program and offers reliable intermittent operation. I will then discuss how these models interact with our latest hardware platform, Capybara, enabling applications to dynamically re-configure the amount of energy continuously required by a region of code and supporting modal energy demands with a single hardware mechanism. I will close with a discussion of recent and upcoming deployment efforts for our intermittent systems work.
Biography: Brandon Lucia is an Assistant Professor of Electrical and Computer Engineering at Carnegie Mellon University. Lucia's lab's work spans programming languages, software and hardware computer systems, and computer architecture. Lucia's lab is defining the area of intermittent computing on energy-harvesting devices, and working on future reliable, efficient parallel computing systems, especially at the edge. Lucia's work has been recognized with a 2018 NSF CAREER Award, the 2018 ASPLOS Best Paper Award, three IEEE MICRO Top Picks in Computer Architecture, a 2015 OOPSLA Best Paper Award, the 2015 Bell Labs Prize, a 2016 Google Faculty Award, and an appointment to the DARPA ISAT study group. His website is https://brandonlucia.com and more information on his lab, which is supported by NSF, Intel, Google, SRC, DARPA, the Kavcic-Moura Fund, and Disney Research, is available at http://intermittent.systems.
Host: Xuehai Qian, xuehai.qian@usc.edu
More Information: 18.11.16 Brandon Lucia_CENG Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Brienne Moore