Jiayun Zhang
Ph.D. Student
Department of Computer Science and Engineering
University of California San Diego
Email: jiayunzhang15 at outlook.com
CV / Google Scholar / GitHub


About Me

I am a first year Ph.D. student in the department of Computer Science and Engineering at UC San Diego. I am co-advised by Prof. Rajesh Gupta and Prof. Jingbo Shang. My research lies in the intersaction of IoT and data mining. Before joining UCSD, I received my B.S. (with honors) in Computer Science from Fudan University, where I was advised by Prof. Yang Chen.

Publications

  • Blacklight: Defending Black-Box Adversarial Attacks on Deep Neural Networks.
    Huiying Li, Shawn Shan, Emily Wenger, Jiayun Zhang, Haitao Zheng, Ben Y. Zhao.
    arXiv preprint arXiv:2006.14042 (2020).

  • Identifying Structural Hole Spanners in Online Social Networks Using Deep Learning.
    Jiayun Zhang, Qingyuan Gong, Yushan Liu, Yang Chen, Xin Wang.
    In Submission.

  • Understanding Work Rhythms in Software Development and Their Effects on Technical Performance.
    Jiayun Zhang, Qingyuan Gong, Yang Chen, Yu Xiao, Xin Wang, Aaron Yi Ding.
    In Submission.

  • Dataset: A video dataset of a wooden box assembly process.
    Jiayun Zhang, Petr Byvshev, Yu Xiao.
    To Appear: the 3rd Workshop on Data Acquisition to Analysis (DATA '20).

  • Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models.
    Shawn Shan, Emily Wenger, Jiayun Zhang, Huiying Li, Haitao Zheng, Ben Y. Zhao.
    Proceedings of the 29th USENIX Security Symposium (USENIX Security), Boston, MA, Aug. 2020.

  • Understanding the Working Time of Developers in IT Companies in China and the United States.
    Jiayun Zhang, Yang Chen, Qingyuan Gong, Aaron Yi Ding, Yu Xiao, Xin Wang, Pan Hui.
    To Appear: IEEE Software. (DOI: 10.1109/MS.2020.2988022).

  • Detecting Malicious Accounts in Online Developer Communities Using Deep Learning.
    Qingyuan Gong, Jiayun Zhang, Yang Chen, Qi Li, Yu Xiao, Xin Wang, Pan Hui.
    Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM), Beijing, China, Nov. 2019.

  • Identifying Structural Hole Spanners in Online Social Networks Using Machine Learning.
    Qingyuan Gong, Jiayun Zhang, Xin Wang, Yang Chen
    Proceedings of the ACM SIGCOMM 2019 Conference Posters and Demos. Beijing, China, Aug. 2019.

  • DeepLoc: A Location Preference Prediction System for Online Lodging Platforms.
    Yihan Ma, Hua Sun, Yang Chen, Jiayun Zhang, Yang Xu, Xin Wang, Pan Hui.
    Proceedings of the 14th CCF Chinese Conference on Computer Supported Cooperative Work (ChineseCSCW), Kunming, China, Aug. 2019.

Research

  • generation

    Defending Black-Box Adversarial Attacks on Deep Neural Networks
    co-advised by Prof. Ben Y. Zhao and Prof. Heather Zheng, University of Chicago. Mar 2020 – Jun 2020
    We propose Blacklight, a novel defense that detects query-based black-box attacks using an efficient similarity engine operating on probabilistic content fingerprints.

  • generation

    Protecting Personal Privacy against Unauthorized Deep Learning Models
    co-advised by Prof. Ben Y. Zhao and Prof. Heather Zheng, University of Chicago. Jan 2020 – Feb 2020
    We propose Fawkes, a system that allow individuals to inoculate themselves against unauthorized facial recognition models by adding imperceptible pixel-level changes to their photos. This work has been published in USENIX Security '20.

  • generation

    Identifying Structural Hole Spanners in Online Social Networks
    advised by Prof. Yang Chen, Fudan University. Mar 2019 – May 2020
    We propose CrossHole, a deep learning-based system for identifying structural hole spanners in online social networks by analyzing the user behaviors and leveraging the cross-site linking function. A poster about this work has been published in SIGCOMM Posters and Demos '19.

  • generation

    Malicious User Identification on Version Control Systems
    advised by Prof. Yang Chen, Fudan University. Jun 2018 – Jun 2019
    We propose GitSec, a system with Phased LSTM and attention mechanism to detect malicious accounts on VCS. This work has been published in CIKM '19.

  • generation

    Understanding Work Rhythms in Software Development
    advised by Prof. Yang Chen, Fudan University. Jan 2019 – Sep 2019
    We identify representative work rhythms of developers by analyzing the commit behaviors and investigate the relationship between work rhythms and technical performance. This work has been accepted by IEEE Software.

  • generation

    A Video and Sensor Dataset of a Wooden Box Assembly Process
    advised by Prof. Yu Xiao, Aalto University. Jun 2019 – Sep 2019
    We collect a video and sensor dataset of the wooden box assembly process with multiple cameras and a sensor glove. This work has been accepted by DATA '20.

  • generation

    Data Mining on Health-Seeking Behavior
    advised by Prof. Yun Xiong, Fudan University. May 2017 – Apr 2018
    We devise a model with SVM for pneumonia detection based on medication records, and a model with Time-Aware LSTM for diabete detection based on previous diagnoses. We also developed a web-based interactive system for diabetes prediction.

Experience

  • generation

    University of Chicago.   Chicago, IL, U.S.A
    Research Assistant at the SAND Lab, co-advised by Prof. Ben Y. Zhao and Prof. Heather Zheng. Jan 2020 – Mar 2020

  • generation

    VMware, Inc.   Shanghai, China
    MTS (Member of Technical Staff) Intern. Apr 2018 – Oct 2018

Selected Awards

  • Outstanding Graduate of Fudan University 2020
  • Chun-Tsung Scholar, Research Endowment Funded by Nobel Laureate Dr. Tsung-Dao Lee 2020
  • The First Prize of Shanghai Open Data Innovation Research Competition (Top 1 among 65 teams) 2019
  • Best Student Award, Mobile Systems and Networking Group in Fudan University (1 out of 32) 2019
  • Second Class Scholarship for Outstanding Students, Fudan University (Top 10%) 2019
  • Xiyuan Scholar, Undergraduate Research Program in Fudan University 2018
  • Third Class Scholarship for Outstanding Students, Fudan University 2016 & 2018

Last updated at Oct 26, 2020 by Jiayun