SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for December
-
Inspiring Trust in Outsourced Computations: From Secure Chip Fabrication to Verifiable Deep Learning in the Cloud
Tue, Dec 05, 2017 @ 01:30 PM - 02:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Professor Siddharth Garg , New York University
Talk Title: Inspiring Trust in Outsourced Computations: From Secure Chip Fabrication to Verifiable Deep Learning in the Cloud
Series: Cyber-Physical Systems Joint Seminar Series
Abstract: Computations are often outsourced by computationally weak clients to computationally powerful external entities. Cloud computing is an obvious example of outsourced computation; outsourced chip manufacturing to offshore foundries or "fabs" is another (perhaps less obvious) example. Indeed, many major semiconductor design companies have now adopted the so-called "fabless" model. However, outsourcing raises a fundamental question of trust: how can the client ascertain that the outsourced computations were correctly performed? Using fabless chip manufacturing and "machine learning as a service (MLaaS)" as exemplars, this talk will highlight the security vulnerabilities introduced by outsourcing computations and describe solutions to mitigate these vulnerabilities.
First, we describe the design of "verifiable ASICs" to address the problem of secure chip fabrication at off-shore foundries. Building on a rich body of work on the "delegation of computation" problem, we enable untrusted chips to provide run-time proofs of the correctness of computations they perform. These proofs are checked by a slower verifier chip fabricated at a trusted foundry. The proposed approach is the first to defend against arbitrary Trojan misbehaviors (Trojans refer to malicious modifications of a chip's blueprint by the foundry) while providing formal and comprehensive soundness guarantees.
Next, we examine the "MLaaS" setting, in which both the training and or inference of machine learning models is outsourced to the cloud. We show that outsourced training introduces new security risks: an adversary can create a maliciously trained neural network (a backdoored neural network, or a BadNet) that has state-of-the art performance on the user's training and validation samples, but behaves badly on specific attacker chosen inputs. We conclude by showing how the same techniques we used design "verifiable ASICs" can be used to verify the results of neural networks executed on the cloud.
Biography: Siddharth Garg is an Assistant Professor in the ECE Department at NYU since Fall 2014 and prior to that, was an Assistant Professor at the University of Waterloo from 2010-2014. His research interests are in secure, reliable and energy-efficient computing. Siddharth was listed in Popular Science Magazine's annual list of "Brilliant 10" researchers in 2016 for his work on hardware security, and is the recipient of an NSF CAREER Award (2015), best paper awards at the IEEE Symposium on Security and Privacy (S&P) 2016, USENIX Security Symposium 2013, at the Semiconductor Research Consortium TECHCON in 2010, and the International Symposium on Quality in Electronic Design (ISQED) in 2009. Siddharth also received the Angel G. Jordan Award from ECE department of Carnegie Mellon University for outstanding thesis contributions and service to the community. He received a Ph.D. in ECE from Carnegie Mellon University, an M.S. degree in EE from Stanford University, and a B.Tech. degree in EE from IIT Madras.
Host: Professor Paul Bogdan
Location: Henry Salvatori Computer Science Center (SAL) - 126
Audiences: Everyone Is Invited
Contact: Talyia White
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Attack-Resilient and Privacy-Preserving Cyber-Physical Systems
Wed, Dec 06, 2017 @ 02:00 AM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Professor Yasser Shoukry, Department of Electrical and Computer Engineering at University of Maryland, College Park.
Talk Title: Attack-Resilient and Privacy-Preserving Cyber-Physical Systems
Series: Cyber-Physical Systems Joint Seminar Series
Abstract: The rapidly increasing dependence on Cyber Physical Systems (CPS) in building critical infrastructures in the context of smart cities, power grids, medical devices, and self-driving cars has opened the gates to increasingly sophisticated and harmful attacks with financial, societal, criminal or political effects. While a traditional cyber attack may leak credit card or other personal sensitive information, a CPS attack can lead to a loss of control in nuclear reactors, gas turbines, the power grid, transportation networks, and other critical infrastructure, placing the Nation's security, economy, and public safety at risk.
In this talk, I will focus on two threat models namely false data injection and Sybil attacks. Under the first threat model, we study the problem of estimating the state of a dynamical system when an adversary arbitrarily corrupts a subset of its sensors. Although of critical importance, this problem is NP hard and combinatorial since the subset of attacked sensors in unknown. Using smart grids and Quadrotors as examples, I will show how to tame the combinatorial nature of the problem using a novel technique named as Satisfiability Modulo Convex Programming or SMC for short. Under the second threat model, and motivated by the crowdsourcing aided road traffic estimation setup, we study the case where a fraction of users (vehicles) are malicious, and report wrong sensory information, or even worse, report the presence of Sybil (ghost) vehicles that do not physically exist. The motivation for such attacks lies in the possibility of creating a "virtual" congestion that can influence routing algorithms, leading to "actual" congestion and chaos. Similarly, to the false data injection attack, our objective is to estimate the state of the physical system (average speed and congestion) from the corrupted information.
While in the previous two threat models we ignored the fact that these, possibly corrupted, sensor information is collected from different agents which may raise several privacy concerns, in the final part of this talk, I will show how to design privacy preserving protocols based on partially homomorphic encryption where data is encrypted before sending it to an untrusted cloud computing infrastructure. The attack resilient algorithms are then computed over the encrypted data without the ability to decrypt it leading to data analytics schemes that are both attack resilient and privacy preserving. I will finish by showing, through multiple experimental results, the real time performance of the proposed algorithms.
Biography: Yasser Shoukry is an Assistant Professor in the Department of Electrical and Computer Engineering at University of Maryland, College Park. He received his Ph.D. in Electrical Engineering from the University of California, Los Angeles in 2015 where he was affiliated with both the Cyber-Physical Systems Lab as well as the Networked and Embedded Systems Lab. Before Joining UMD, Yasser spent two years as a joint post-doctoral associate at UC Berkeley, UCLA, and UPenn. Before pursuing his Ph.D. at UCLA, he spent four years as an R&D engineer in the industry of automotive embedded systems. Yasser's research interests include the design and implementation of resilient Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) by drawing on tools from embedded systems, formal methods, control theory, and machine learning
Prof. Shoukry is the recipient of the Best Demo Award from the ACM/IEEE IPSN conference in 2017, the Best Paper Award from the ACM/IEEE ICCPS in 2016, the Distinguished Dissertation Award from UCLA EE department in 2016 and the UCLA Chancellor's prize in 2011/2012. In 2015, he led the UCLA/Caltech/CMU team to win the NSF Early Career Investigators (NSF-ECI) research challenge. His team represented the NSF-ECI in the NIST Global Cities Technology Challenge, an initiative designed to advance the deployment of Internet of Things (IoT) technologies within a smart city.
Host: Professor Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Requirements Engineering Challenges for Cyber-Physical Systems
Thu, Dec 07, 2017 @ 01:30 PM - 02:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Jim Kapinski, Ph.D., Model-Based Development, Toyota Technical Center
Talk Title: Requirements Engineering Challenges for Cyber-Physical Systems
Series: Cyber-Physical Systems Joint Seminar Series
Abstract: Cyber-physical systems (CPSs) are used in many mission critical applications, such as automobiles, aircraft, and medical devices; and the complexity of these systems is growing rapidly. New analysis techniques are available to increase confidence in the reliability of CPSs, but most methods rely on the availability of formal system requirements, which can be challenging to develop for complex applications. This talk presents promising recent developments in verification and validation for CPS, including formal methods and automated testing techniques, and addresses ongoing challenges related to the development of formal requirements.
Biography: Jim Kapinski received his Ph.D. in Electrical and Computer Engineering from Carnegie Mellon University in 2005 and was a postdoctoral researcher at CMU from 2007 to 2008. He went on to found and lead Fixed-Point Consulting, serving clients in the defense, aerospace, and automotive industries. Since 2012 he has been with the Model-Based Development group at the Toyota Technical Center. His work at Toyota focuses on advanced research into verification techniques for embedded software for powertrain control systems. Jim's research interests include verification techniques for embedded control system designs and analysis of hybrid dynamical systems.
Host: Professor Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia Whtie
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Taking the Internet of Things out of the Lab and into Industry 4.0
Tue, Dec 12, 2017 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Danny Hughes, Professor at KU Leuven and CTO of Versasense
Talk Title: Taking the Internet of Things out of the Lab and into Industry 4.0
Series: Cyber-Physical Systems Joint Seminar Series
Abstract: This talk presents the author's experiences of commercializing academic Internet of Things (IoT) research. It will begin with an overview of recent IoT research conducted by the DistriNet research group of KU Leuven and the reason we took the plunge to incorporate an IoT spin-off company -” VersaSense. The presentation will then discuss our experiences -” good and bad -” of deploying contemporary IoT technologies in industrial scenarios, with a focus on the gap that exists between contemporary academic research and the industrial IoT. The talk will be illustrated with a number of demonstrations and examples drawn from running real-world systems.
Biography: Danny is the Chief Technical Officer of Versasense NV, an Internet of Things spin-off company that provides end-to-end IoT solutions. He is also a Professor with the Department of Computer Science of KU Leuven (Belgium), where he is a member of the DistriNet (Distributed Systems and Computer Networks) research group and leads the Networked Embedded Software task-force. Danny holds a PhD from Lancaster University (UK) and has since worked as a Visiting Scholar with the University of California at Berkeley (USA), a Visiting Scholar with the University of Sao Paulo (Brazil) and as a Lecturer with Xi'an Jiaotong-Liverpool University (China). His PhD focused on Peer-to-Peer (P2P) systems and his current research is on distributed software systems and the Internet of Things (IoT).
Host: Professor Bhaskar Krishnamachari
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Talyia White
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
