Wenqi Wei


School of Computer Science

College of Computing

Georgia Institute of Technology

Email: wenqiwei@gatech.edu

Address: 3319,KACB, 266 Ferst Dr NW, Atlanta, GA 30318

Biography

I am currently a Ph.D candidate at Georgia Institute of Technology (expected graduation 2022 Spring). I work with Professor Ling Liu in the Distributed Data Intensive Systems Lab (DiSL).

My research interest includes security and trust enhanced machine learning and AI systems, data privacy, AI ethics (fairness, accountability, transparency), data mining and analysis, and machine learning service with a current focus on deep learning and federated learning. You are welcome to visit my homepage for up-to-date research activities.

Prior to attending at Georgia Tech, I received my Bachelor's degree in Electronics and Information Engineering (B.E.) with summa cum laude from Huazhong University of Science and Technology. I worked as an undergradute research assistant in Signal Processing and Information Networking in Communication Lab (SINCLab), Wuhan National Laboratory for Optoelectronics for two years (2015-2017), under the supervision of Professor Pan Zhou.

I lived in Atlanta, Georgia when I was a teenager, and attended Samuel M. Inman Middle School and Henry W. Grady High School (now Midtown High School). I graduted from Inman with Awards for Achieving Highest Average in Science, Outstanding Achievement in ESOL, CRCT (Math & Science), and Honor Roll Certificate.

Ongoing Research Projects

1. AI robustness: Research on identifying and mitigating AI vulnerabilities including poisoning and backdoor at training phase and adversarial example and outlier input at inference phase. [XEnsemble project] [Security4AI vLab]

2. AI privacy: Research on identifying privacy intrusion in AI systems and designing privacy-preserving machine learning solutions. [CPL attack] [AI-Privacy vLab]

3. AI fairness: Research on eliminating algorithmic bias and improving accountability and transparency of AI systems.

4. Machine Learning Services: Research on machine learning algorithm and system design, performance measurement (benchmarking) and model optimization (model compression and ensemble learning). Delivering AI/privacy/security solutions to data systems.

5. Data Mining: Research on data mining with representation learning (graph embedding, graph neural networks and distributed data mining), privacy-preserving data utilization and machine learning-based system security.

Experience

Aug. 2017 - present                       RA in the School of CS, Georgia Tech
Fall 2019, 2020, 2021                     TA, CS6220 Big Data Systems, Georgia Tech
Spring 2019                                      TA, CS6675 Advanced Internet Computing, Georgia Tech
Summer 2019, 2020, 2021            Research intern, IBM Research
Summer 2018                                  Research intern, Samsung Research America
Sep. 2013 - Jun. 2017                     Undergraduate Student, received Bachelor in Engineering Degree in June 2017, HUST

Publication

*** CCF B or higher are highlighted with bold.
[C15] Yanzhao Wu, Ling Liu, Zhongwei Xie, Ka-Ho Chow, and Wenqi Wei. "Boosting Ensemble Accuracy by Revisiting Ensemble Diversity Metrics", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, Tennessee. June 2021. (virtual)  [pdf]
[C14] Wenqi Wei, Ling Liu, Yanzhao Wu, Gong Su, and Arun Iyengar. "Gradient-Leakage Resilient Federated Learning", IEEE International Conference on Distributed Computing Systems (ICDCS), Washington DC, USA. USA. July 2021. (virtual)  [pdf]
[C13] Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, and Yanzhao Wu. "Cross-layer Strategic Ensemble Defense against Adversarial Examples". International Conference on Computing, Networking and Communications (ICNC), Big Island, Hawaii, USA. February 2020.  [pdf]
[C12] Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, and Yanzhao Wu. "A Framework for Evaluating Gradient Leakage Attacks in Federated Learning". European Symposium on Research in Computer Security (ESORICS), Guildford, UK. September 2020. (virtual)  [pdf]
[C11] Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy, Stacey Truex, Wenqi Wei, and Yanzhao Wu. "Understanding Object Detection Through An Adversarial Lens". European Symposium on Research in Computer Security (ESORICS), Guildford, UK. September 2020. (virtual)  [pdf]
[C10] Stacey Truex, Ling Liu, Ka-Ho Chow, Mehmet Emre Gursoy, and Wenqi Wei. "LDP-Fed: federated learning with local differential privacy". ACM International Workshop on Edge Systems, Analytics and Networking (EdgeSys), Heraklion, Crete, Greece. April 2020 (Best paper). (virtual)  [pdf]
[C9] Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, and Yanzhao Wu, "Adversarial Deception in Deep Learning: Analysis and Mitigation", IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS), Atlanta, Georgia, USA. December 2020. (virtual)  [pdf]
[C8] Ka-Ho Chow, Ling Liu, Margaret Loper, Mehmet Emre Gursoy, Stacey Truex, Wenqi Wei and Yanzhao Wu, "Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems", IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS), Atlanta, Georgia, USA. December 2020. (virtual)  [pdf]
[C7] Yanzhao Wu, Ling Liu, Zhongwei Xie, Juhyun Bae, Ka-Ho Chow, and Wenqi Wei, "Promoting High Diversity Ensemble Learning with EnsembleBench", IEEE International Conference on Cognitive Machine Intelligence (CogMI), Atlanta, Georgia, USA. December 2020. (virtual)  [pdf]
[C6] Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, and Ling Liu, “Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks.” IEEE International Conference on Big Data (Big Data), Los Angeles, California, USA. December 2019.  [pdf]
[C5] Yanzhao Wu, Ling Liu, Juhyun Bae, Ka-Ho Chow, Arun Iyengar, Calton Pu, Wenqi Wei, Lei Yu, and Qi Zhang, “Demystifying Learning Rate Polices for High Accuracy Training of Deep Neural Networks.” IEEE International Conference on Big Data (Big Data), Los Angeles, California, USA. December 2019.  [pdf]
[C4] Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Wenqi Wei, and Lei Yu, “Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability.” IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS), Los Angeles, California, USA. December 2019.  [pdf]
[C3] Ling Liu, Wenqi Wei, Ka-Ho Chow, Margaret Loper, Mehmet Emre Gursoy, Stacey Truex, and Yanzhao Wu, "Deep Neural Network Ensembles against Deception: Ensemble Diversity, Accuracy and Robustness", IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS), Monterey, California, USA. November 2019.  [pdf]
[C2] Mehmet Emre Gursoy, Ling Liu, Stacey Truex, Lei Yu, Wenqi Wei. "Utility-aware synthesis of differentially private and attack-resilient location traces", ACM Conference on Computer and Communications Security (CCS), Toronto, Canada. October 2018.  [pdf]
[C1] Liu, Ling, Yanzhao Wu, Wenqi Wei, Wenqi Cao, Semih Sahin, and Qi Zhang. "Benchmarking Deep Learning Frameworks: Design Considerations, Metrics and Beyond." IEEE International Conference on Distributed Computing Systems (ICDCS), Vienna, Austria. July 2018.  [pdf]
[J7] Jingya Zhou, Ling Liu, Wenqi Wei, and Jianxi Fan "Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding", accepted by ACM Computing Surveys. 2021.
[J6] Wenqi Wei, and Ling Liu, "Robust Deep Learning Ensemble against Deception", IEEE Transactions on Dependable and Secure Computing (TDSC), 18(4), 1513-1527, 2021.  [pdf]
[J5] Wenqi Wei, Qi Zhang, and Ling Liu, "Bitcoin Transaction Forecasting with Deep Network Representation Learning", IEEE Transactions on Emerging Topics in Computing, 9(3), 1359-1371, 2021.  [pdf]
[J4] Mehmet Emre Gursoy, Acar Tamersoy, Stacey Truex, Wenqi Wei, and Ling Liu, "Secure and Utility-Aware Data Collection with Condensed Local Differential Privacy", IEEE Transactions on Dependable and Secure Computing (TDSC), 18(5), 2365-2378, 2021.  [pdf]
[J3] Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Lei Yu, and Wenqi Wei, "Demystifying Membership Inference Attacks in Machine Learning as a Service", accepted by IEEE Transactions on Services Computing (TSC).  [pdf]
[J2] Yanzhao Wu, Ling Liu, Calton Pu, Wenqi Cao, Semih Sahin, Wenqi Wei, and Qi Zhang, "A Comparative Measurement Study of Deep Learning as a Service Framework", accepted by IEEE Transactions on Services Computing (TSC).  [pdf]
[J1] Pan Zhou*, Wenqi Wei*, Kaigui Bian, Dapeng Oliver Wu, Yuchong Hu, Qian Wang. "Private and Truthful Aggregative Game for Large-Scale Spectrum Sharing", IEEE Journal on Selected Areas in Communications (JSAC), 35(2), 463-477, 2017. (* equal contribution)  [pdf]
[preprint1] Wenqi Wei, Ling Liu, Margaret Loper, Stacey Truex, Lei Yu, Mehmet Emre Gursoy,and Yanzhao Wu, "Adversarial Examples in Deep Learning: Characterization and Divergence", arXiv preprint arXiv:1807.00051 (2018).  [pdf]
[poster1] Wenqi Wei, Yanzhao Wu, Ling Liu. "DeepEyes: Integrating Deep Learning and Crowd Sourcing for Localization", Southern Data Science Conference, Atlanta, Georgia 2018 (research track poster).

Presentation and talks

IEEE ICDCS, Washington DC, USA, Jul. 7-10, 2021.

IEEE TPS, Atlanta, GA, USA, Dec. 1-3, 2020.

ESORICS, Guildford, UK, Sep. 14-18, 2020.

IEEE MASS, Monterey, CA, USA. Nov.4-7, 2019.

Cybersecurity Summit, Institute for Information Security & Privacy, Atlanta, GA, USA, Sep. 10, 2019

Cybersecurity Summit, Institute for Information Security & Privacy, Atlanta, GA, USA, Oct. 4, 2018

Southern Data Science Conference, Atlanta, GA, USA, Apr. 13-14, 2018

Service

Reviewer:

   Conference: ICDE18, ICDM (20,21), WWW21, ICLR-DPML21, KDD21, MM21, Middleware21, NeurIPS-AI4Science21, AAAI22,

   Journal: IEEE TIFS, IEEE TMC, IEEE TNSE, IEEE IoTJ, IEEE CL, ACM TOIT, JISA, CHB, SCIS,

Program Committee:

   Conference: NeurIPS-ML4H (20,21), SDM22