Select a calendar:
Filter January Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for January 24, 2018
-
Adversarial Machine Learning: The Case of Optimal Attack Strategies Against Recommendation Systems
Wed, Jan 24, 2018 @ 10:30 AM - 11:30 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Negar Kiyavash, Associate Professor/UIUC
Talk Title: Adversarial Machine Learning: The Case of Optimal Attack Strategies Against Recommendation Systems
Abstract: Adversarial machine learning which lies in the intersection of learning and security aims to understand the effects of adversaries on learning algorithms and safe guard against them by design of protection mechanisms. In this talk, we discuss the effect of strategic adversaries in recommendation systems. Such systems can be modeled using a multistage sequential prediction framework where at each stage, the recommendation system combines the predictions of set of experts about an unknown outcome with the aim of accurately predicting the outcome. The outcome is often the "rating/interest" of a user in an item. Specifically, we study an adversarial setting in which one of the experts is malicious and his goal is to impose the maximum loss on the system. We show that in some settings the greedy policy of always reporting false prediction is asymptotically optimal for the malicious expert. Our result could be viewed as a generalization of the regret bound for learning from expert advice problem in the adversarial setting with respect to the best dynamic policy, rather than the conventional regret bound for the best action (static policy) in hindsight.
Biography: Negar Kiyavash is Willett Faculty Scholar at the University of Illinois and a joint Associate Professor of Industrial and Enterprise Engineering and Electrical and Computer Engineering. She is also affiliated with the Coordinated Science Laboratory (CSL) and the Information Trust Institute. She received her Ph.D. degree in electrical and computer engineering from the University of Illinois at Urbana-Champaign in 2006. Her research interests are in design and analysis of algorithms for network inference and security. She is a recipient of NSF CAREER and AFOSR YIP awards and the Illinois College of Engineering Dean's Award for Excellence in Research.
Host: Sandeep Gupta, sandeep@usc.edu, x02251
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
Secure Hardware Platforms for the Internet of Things (IoT)
Wed, Jan 24, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Srini Devadas, Massachusetts Institute of Technology
Talk Title: Secure Hardware Platforms for the Internet of Things (IoT)
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: The Internet is expanding into the physical world, connecting billions of devices. In this Internet of Things, two contradictory trends are appearing. On the one hand, the cost of security breaches is increasing as we place more responsibilities on the devices that surround us. On the other hand, wireless computing elements are becoming small, unsupervised, and physically exposed. Unfortunately, existing systems do not address many new attacks, such as resource sharing and physical attacks.
Hardware to the rescue! This talk will describe how secure systems can be built from the ground up. Physical Unclonable Functions (PUFs) are a tamper resistant way of establishing shared secrets with a physical device. They rely on the inevitable manufacturing variations between devices to produce private keys that can be used as a hardware root of trust in a secure processor. Architectural isolation can be used to secure computation on a remote secure processor with a private key where the privileged software is potentially malicious as recently deployed by Intel's Software Guard Extensions (SGX). The Sanctum secure processor architecture offers the same promise as SGX, namely strong provable isolation of software modules running concurrently and sharing resources, but is much more lightweight and protects against an important class of additional software attacks that infer private information by exploiting resource sharing.
Biography: Srini Devadas is the Webster Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT) where he has been on the faculty since 1988. Devadas's research interests span Computer-Aided Design (CAD), computer security and computer architecture. He is a Fellow of the IEEE and ACM. He has received the 2014 IEEE Computer Society Technical Achievement award, the 2015 ACM/IEEE Richard Newton technical impact award, and the 2017 IEEE Wallace McDowell award for his research. Devadas is a MacVicar Faculty Fellow and an Everett Moore Baker teaching award recipient, considered MIT's two highest undergraduate teaching honors.
Host: Professor Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
Networking
Wed, Jan 24, 2018 @ 04:30 PM - 05:30 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Learn important networking skills
Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: All Viterbi
Contact: RTH 218 Viterbi Career Connections
-
ASBME Corporate Info Session
Wed, Jan 24, 2018 @ 07:00 PM - 08:00 PM
Viterbi School of Engineering Student Organizations
Student Activity
Let us help you impress corporate representatives at ASBME's corporate dinner and Viterbi's Career Fair! ASBME President Holly Huber will be holding an informal Q&A on all-things corporate-from application timelines from prominent companies that recruit at USC, to what to talk about with reps at networking events. Come with questions! This event will be taking place in TCC 227 at 7 PM.
Location: Ronald Tutor Campus Center (TCC) - 227
Audiences: Everyone Is Invited
Contact: Associated Students of Biomedical Engineering
