Logo: University of Southern California

Events Calendar



Select a calendar:



Filter December Events by Event Type:



Events for December 05, 2017

  • 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

    OutlookiCal
  • CAIS Seminar: Dr. Barath Raghavan (International Computer Science Institute) - Top-down Computing Systems for Bottom-up Social Good

    Tue, Dec 05, 2017 @ 02:00 PM - 03:00 PM

    Thomas Lord Department of Computer Science

    Conferences, Lectures, & Seminars


    Speaker: Dr. Barath Raghavan, International Computer Science Institute

    Talk Title: Top-down Computing Systems for Bottom-up Social Good

    Series: Center for AI in Society (CAIS) Seminar Series

    Abstract: Dr. Raghavan will discuss three topics: 1) rural network access, 2) agroecological development, and 3) air pollution mitigation, all in which computational systems that enable top-down planning can enable bottom-up instantiations. He will describe systems he developed for increasing access to the Internet in rural areas, ongoing work on new models and planning systems for shifting food production to more sustainable practices, and planned future work on enlisting community members to organize to mitigate air pollution.

    Biography: Dr. Raghavan is in the process of joining the faculty in computer science at USC. He is a senior researcher at the International Computer Science Institute and leads the engineering team at Nefeli Networks, both in Berkeley, CA. He received his BS in EECS from UC Berkeley in 2002 and PhD in Computer Science from UC San Diego in 2009.


    Host: Milind Tambe

    Location: Ronald Tutor Hall of Engineering (RTH) - 526

    Audiences: Everyone Is Invited

    Contact: Computer Science Department

    OutlookiCal
  • PhD Defense - Nicholas Rotella

    Tue, Dec 05, 2017 @ 02:00 PM - 04:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Tuesday, December 5th, 2 p.m. to 4 p.m, RTH 406

    PhD Candidate: Nicholas Rotella

    Title: Estimation-based control for humanoid robots

    Abstract:
    As sensor, actuator and processor technology continues to improve, humanoid robots have become more common in both academic and industrial environments. These robots have the potential to operate in complex environments built for humans given their form factor. However, the challenge of operating autonomously in unknown environments involves obtaining accurate estimates of the robot's state by fusing information from on-board sensors, and using these estimates for control in ways which allow robustness to uncertainty and disturbances. In this work, we propose methods for estimating important states of humanoid robots and evaluate the role of sensory information and state estimation in executing behaviors on a torque-controlled humanoid.

    Committee:
    Stefan Schaal
    Ludovic Righetti
    Laurent Itti
    James Finley

    Location: 406

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • Epstein Department - Guest Speaker Event

    Tue, Dec 05, 2017 @ 03:30 PM - 04:50 PM

    Daniel J. Epstein Department of Industrial and Systems Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dr. Ward Romeijnders, Assistant Professor, University of Groningen

    Talk Title: Convex Approximations For Mixed-Integer Recourse Models

    Host: Prof. Suvrajeet Sen

    More Information: Ward Romeijnders_flyer.pdf

    Location: Ethel Percy Andrus Gerontology Center (GER) - GER 206

    Audiences: Everyone Is Invited

    Contact: Grace Owh

    OutlookiCal