Logo: University of Southern California

Events Calendar



Select a calendar:



Filter March Events by Event Type:



Events for March 28, 2023

  • ECE-S Seminar - Dr Yupeng Zhang

    Tue, Mar 28, 2023 @ 10:00 AM - 11:00 AM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dr Yupeng Zhang, Assistant Professor | Department of Computer Science and Engineering, Texas A&M University

    Talk Title: Zero-Knowledge Proofs: from Theory to Practice

    Abstract: A zero-knowledge proof is a powerful cryptographic tool to establish trust without revealing any sensitive information. It allows one party to convince others that a claim about the properties of secret data is true, while the data remains confidential. Zero-knowledge proofs have been widely used in blockchains and crypto-currencies to enhance privacy and improve scalability. They can also be applied to prove the fairness and integrity of machine learning inferences and the correctness of program analysis.
    In this talk, I will present my research in this area to bring zero-knowledge proofs from theory to practice with new efficient algorithms. In the first part, I will talk about a new framework to build general-purpose zero-knowledge proofs for any computations.

    In this framework, we were able to develop the first zero- knowledge proof scheme with a linear proof generation time. In the second part, I will talk about our recent works on new applications of zero-knowledge proofs in machine learning and program analysis. The scalability and efficiency of the schemes can be further improved with new sublinear algorithms. Finally, I will discuss my future research plans, including memory-efficient and distributed algorithms for scalable blockchains and smart contracts, privacy-preserving machine learning, and cloud computing with full security and privacy.

    Biography: Yupeng Zhang is an assistant professor in the Computer Science and Engineering department at the Texas A&M University. His research is in the area of cybersecurity and applied cryptography, developing efficient and scalable cryptographic protocols to enhance the security and privacy of data and computations in real-world applications. He has been working on zero-knowledge proofs, secure multiparty computations, and their applications in blockchain, machine learning and program analysis. He has published many papers in top security and cryptography conferences including S&P, CCS, USENIX Security and Crypto. He is the recipient of the NSF CAREER award, the Facebook Faculty award, the ACM SIGSAC best dissertation award runners-up and the Google PhD fellowship. Before joining Texas A&M, he was a postdoctoral researcher at UC Berkeley, and he obtained his Ph.D. from the University of Maryland.

    Host: Dr Sandeep Gupta, sandeep@usc.edu | Dr Murali Annavaram, annavara@usc.edu

    More Information: ECE Seminar Announcement 03.27.2023 - Yupeng Zhang.pdf

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 248

    Audiences: Everyone Is Invited

    Contact: Miki Arlen

    OutlookiCal
  • CS Colloquium: Kexin Pei (Columbia University) - Analyzing and Securing Software via Robust and Generalizable Learning

    Tue, Mar 28, 2023 @ 11:00 AM - 12:00 PM

    Thomas Lord Department of Computer Science

    Conferences, Lectures, & Seminars


    Speaker: Kexin Pei, Columbia University

    Talk Title: Analyzing and Securing Software via Robust and Generalizable Learning

    Series: CS Colloquium

    Abstract: Software is powering every aspect of our society, but it remains plagued with errors and prone to critical failures and security breaches. Program analysis has been a predominant technique for building trustworthy software. However, traditional approaches rely on hand-curated rules tailored for specific analysis tasks and thus require significant manual effort to tune for different applications. While recent machine learning-based approaches have shown some early promise, they, too, tend to learn spurious features and overfit to specific tasks without understanding the underlying program semantics.

    In this talk, I will describe my research on building machine learning (ML) models toward learning program semantics so they can remain robust against transformations in program syntax and generalize to various program analysis tasks and security applications. The corresponding research tools, such as XDA, Trex, StateFormer, and NeuDep, have outperformed commercial tools and prior arts by up to 117x in speed and by 35% in precision and have helped identify security vulnerabilities in real-world firmware that run on billions of devices. To ensure the developed ML models are robust and generalizable, I will briefly describe my research on building testing and verification frameworks for checking the safety properties of deep learning systems. The corresponding research tools, such as DeepXplore, DeepTest, ReluVal, and Neurify, have been adopted and followed up by the industry, been covered in media such as Scientific American, IEEE Spectrum, Newsweek, and TechRadar, and inspired over thousands of follow-up projects.


    This lecture satisfies requirements for CSCI 591: Research Colloquium

    Biography: Kexin Pei is a Ph.D. candidate in Computer Science at Columbia University, advised by Suman Jana and Junfeng Yang. His research lies at the intersection of security, software engineering, and machine learning, with a focus on building machine-learning tools that utilize program structure and behavior to analyze and secure software. His research has received the Best Paper Award in SOSP, an FSE Distinguished Artifact Award, been featured in CACM Research Highlight, and won CSAW Applied Research Competition Runner-Up. He was part of the learning for code team when he interned at Google Brain, building program analysis tools based on large language models.

    Host: Jiapeng Zhang

    Location: Olin Hall of Engineering (OHE) - 132

    Audiences: Everyone Is Invited

    Contact: Assistant to CS chair

    OutlookiCal
  • Epstein Institute - ISE 651 Seminar

    Tue, Mar 28, 2023 @ 03:30 PM - 04:50 PM

    Daniel J. Epstein Department of Industrial and Systems Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dr. Gino Lim, Professor and Dept. Chair, Department of Industrial Engineering, University of Houston

    Talk Title: A Chance Constrained Programming Framework to Handle Uncertainties in Radiation Therapy Treatment Planning

    Host: Dr. Sze-chuan Suen

    More Information: March 28, 2023.pdf

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

    Audiences: Everyone Is Invited

    Contact: Grace Owh

    OutlookiCal
  • Lockheed Martin Hypersonics Tech Talk

    Tue, Mar 28, 2023 @ 04:00 PM - 07:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    Lockheed Martin is showing Top Gun Maverick! Come join us for movie night and a Hypersonics Tech Talk!

    Date: Tuesday, March 28th
    Time: 4:00 p.m. - 7:00 p.m.
    Location: Michelson Hall (MCB) 101

    Lockheed Martin is a world-leader in the field of Hypersonics. Please join us to learn about our exciting work, and our collaboration with Paramount Pictures on the blockbuster movie Top Gun Maverick.

    There will be popcorn and candy!

    Please RSVP on gateway and also HERE

    What majors and class levels are you interested in connecting with? All levels, AE, ME, EE/Comp E, Materials, IE/SysE, and CS majors.

    Are you recruiting for internships, full time, or both? Pipelining for 2024 events.

    Can you offer Visa sponsorship? Are you able to hire a student on CPT or OPT? No, sorry.

    Location: Michelson Center for Convergent Bioscience (MCB) - 101

    Audiences: Everyone Is Invited

    Contact: RTH 218 Viterbi Career Connections

    OutlookiCal