Wenqi Wei, PhD Tenure-track Faculty, ex-IBMer Computer and Information Sciences Department Fordham University Email: wenqiwei@fordham.edu Address: 610H, 113 West 60th street, New York City, NY 10023 "Talk is cheap, show me the code." [Curriculum_vitae]

News

• Research Group Recruitment

  We have PhD openings with guaranteed support for 5 years (Deadline every year around mid January). You are welcome to contact me regarding the PhD in Computer Science opportunities.

• Research Group Recruitment

  I am always looking for self-motivated students/scholars to work on trustworthy AI, big data analysis, and/or whatever topics identified by our collaborators at IBM Research/Cisco Research/Google/Meta/... Please read these core values from Meta before contacting me, and include your CV and intention of interests in the email. Recently, I am interested in security and privacy in LLMs and diffusion models, as well as AI-driven information systems.

• Call for Paper

  I am honored to serve as the PC co-chair for IEEE CIC 2025. Please consider submitting your latest research contributions and joining us in advancing the field. See you in Pittsburgh!

• Jun 2025 Our paper "On the Adversarial Robustness of Graph Neural Networks with Graph Reduction" has been accepted to ESORICS25.
• Feb 2025 Congratulate Xiang on his first paper named "Where are we in audio deepfake detection? A systematic analysis over generative and detection models" being accepted to ACM TOIT.
• Feb 2025 I am honored to serve as the tutorial chair for IEEE International Conference on Big Data 2025.
• Sep 2024 I am honored to serve as the workshop chair for ACM CODASPY 2025.
• Sep 2024 Our book chapter "Data Poisoning and Leakage Analysis in Federated Learning" in Handbook of Trustworthy Federated Learning has been published.
• May 2024 I am honored to serve as an associate editor for ACM TOIT.
• May 2024 Our paper "Diversity-driven Privacy Protection Masks Against Unauthorized Face Recognition" has been accepted to PETS24.
• Apr 2024 Our paper "Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control" has been accepted to IJCAI24.
• Jan 2024 Our paper "Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance" has been accepted to ACM Computing Surveys.
• Jan 2024 One paper on efficient training of language models for Ethereum Fraud Detection has been accepted to TheWebConf 2024.
• Dec 2023 Our paper "Demystifying Data Poisoning Attacks in Distributed Learning as a Service" has been accepted to IEEE Trans. Services Computing.
• Sep 2023 Two papers on privacy analysis and adversarial robustness have been accepted to IEEE ICDM23.
• Aug 2023 I am honored to serve as the tutorial co-chair for IEEE International Conference on Big Data 2023.
• May 2023 Our paper "Securing Distributed SGD against Gradient Leakage Threats" has been accepted to IEEE TPDS.
• Feb 2023 Our paper "STDLens: Securing Federated Learning Against Model Hijacking Attacks" has been accepted to CVPR23.
• Oct 2022 I am being added to the Distinguished Review Board for ACM Transactions on the Web (appointed 2023-2025).

Biography

I am currently a tenure-track assistant professor at Fordham University. I received my PhD in Computer Science from Georgia Institute of Technology in 2022. I was fortunate to work with Professor Ling Liu in the Distributed Data Intensive Systems Lab (DiSL). After graduation, I spent some short but wonderful time at IBM Research. I received my Bachelor's degree in Electronics and Information Engineering (B.E.) with summa cum laude from Huazhong University of Science and Technology.

My research interest includes trustworthy data management and systems, data privacy, responsible data analysis (fairness, accountability, transparency), intelligent data management (for financial service, healthcare, and misinformation) with particular focus on representation learning, online learning (multi-armed bandits), and foundation models. You are welcome to visit my homepage for up-to-date research activities.

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

SPAM: Secure and Private AI Management

1. AI Robustness: identifying and mitigating vulnerabilities in AI-driven data systems and services.

• Adversarial Robustness [TDSC¹] [ESORICS20¹][ESORICS25]
• Poisoning Robustness [CVPR23] [IJCAI24]

2. AI Privacy: identifying privacy intrusion attacks in AI-driven data systems and designing privacy-preserving solutions.

• Privacy Intrusion Attacks [ESORICS20²]
• Local Differential Privacy Solutions [TDSC²] [TIFS¹]
• Differentially Private Solutions [ICDCS21] [ICDM23¹] [TIFS²] [TPDS]

3. AI Fairness: eliminating algorithmic bias and improving accountability and transparency of AI-driven data systems.

4. Intelligent Data Service: delivering AI/privacy-preserving/security-aware solutions to intelligent data systems.

• Privacy-Preserving Data Services [JSAC] [CCS18] [PET24]
• Ensemble Learning [CVPR21] [ICDM23²] [TIST]
• AI for Cybersecurity Solutions [BigData22] [BigData23] [theWebConf24]
• Quantum Data Services [QCE24]
• LLM for Financial Data Services [BigData24] [TBD]

5. AI and Cybersecurity Management: Research on implications, management, regulation and policy of AI and cybersecurity in modern information sytems.

• Trustworthy AI Management [TSC¹] [TSC²] [CSUR¹][TOIT¹]
• AI-driven Informations System Management [ICDCS18] [BigData19] [TSC³] [CSUR²]

Selected Publications

See [Google Scholar] for full list.

- Wenqi Wei and Ling Liu, "Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance", accepted by ACM Computing Surveys (CSUR). 2025.

- Ka-Ho Chow, Wenqi Wei, Lei Yu, "Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control", International Joint Conference on Artificial Intelligence (IJCAI), Jeju, August 2024.

- Wenqi Wei, Ka-Ho Chow, Yanzhao Wu, and Ling Liu. "Demystifying Data Poisoning Attacks in Distributed Learning as a Service", accepted by IEEE Transactions on Services Computing (TSC), 2024.  [pdf]

- Wenqi Wei, Ling Liu, Jingya Zhou, Ka-Ho Chow, and Yanzhao Wu. "Securing Distributed SGD against Gradient Leakage Threats", accepted by IEEE Transactions on Parallel and Distributed Systems (TPDS), 2023.  [pdf]

- Wenqi Wei, and Ling Liu. "Gradient Leakage Attack Resilient Deep Learning", IEEE Transactions on Information Forensics and Security (TIFS), vol. 17, pp. 303-316, 2022.  [pdf]

- 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]

- Ka-Ho Chow, Ling Liu, Wenqi Wei, Fatih Ilhan, Yanzhao Wu. "STDLens: Securing Federated Learning Against Model Hijacking Attacks.", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, June 2023.

- 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]

- 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]

- 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]

Seminars and talks

Speaker, NYC Privacy Day, Columbia University, Apr. 18, 2025.

Guest lecture, MIS 185N Technical Dimensions of Cybersecurity, McCombs School of Business, UT-Austin, Apr. 2, 2025.

Information Management Research Seminar, McCombs School of Business, UT-Austin, Feb. 14， 2025.

Fordham Data Science Symposium, Fordham University, NYC, NY, USA, Apr. 11, 2024.

Guest lecture, MIS 185N Technical Dimensions of Cybersecurity, McCombs School of Business, UT-Austin, Apr. 3, 2024.

NSF SFS @ Fordham Center for CyberSecurity, NYC, NY, USA, Nov. 30, 2023.

Fordham Data Science Symposium, Fordham University, NYC, NY, USA, Apr. 11, 2023.

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

Teaching

CISC6000 Deep Learning @ Fordham (instructor)

CISC5325 Databases @ Fordham (instructor)

CISC5835 Algorithms for Data Science @ Fordham (instructor)

CISC4080 Computer Algorithms @ Fordham (instructor)

CS6675 Advanced Internet Computing @ Georgia Tech (TA)

CS6220 Big Data Systems @ Georgia Tech (TA)

Service

Conference Program and Organizing Committee:

   Program Committee: NeurIPS-ML4H (20,21,22), ML4H23, ICLR-DPML21, NeurIPS-AI4Science21, ICML-AI4Science22, TPS(22,23,24,25), SDM(22,24), NeurIPS(22,23,24，25), KDD(21,22,23,24,25,26), ECCV(22,24), CVPR(22,23,24), VTC23, ICWSM(23,24,25,26), AAAI(23,24,25,26), TheWebConf23, IJCAI(23,24), ICCV(23,25), ISI23, HICSS24, WACV24, ICLR(24,25), SACMAT(24,25), CODASPY25, ICML25, ESORICS25

   Senior Program Committee: AAAI23-SRAI track

   Chairing: Publicity chair @ CIC/TPS/CogMI(22,23), Mentoring Workshop Chair @ CIC/TPS/CogMI (23,24), Session chair @ (AAAI23, CIC/TPS/CogMI23,24), Tutorial chair @ (IEEE BigData23, IEEE BigData25), Workshop chair @ CIC/TPS/CogMI24, Workshop chair @ CODASPY25, PC chair @ IEEE CIC25

Reviewer and Editor:

   Associate Editor: ACM TOIT

   Guest Editor: ACM TOIT SI on Reliable Infrastructure and Edge Analytics for IoT, JSA SI on Efficient and Secure Computing and Data Systems

   Distinguished Review Board: ACM TWEB

   Journal Reviewer: IEEE TIFS, IEEE TKDE, IEEE TSC, IEEE ToN, IEEE TNNLS, IEEE TBD, IEEE TP, IEEE TNSE, IEEE TETC, IEEE IoTJ, IEEE CL, ACM TOIT, ACM CSUR, ACM TIST, ACM TWEB, Elsevier CHB, Elsevier JISA, Elsevier IP&M, Springer ISF, Springer ML, Springer SCIS, SCN,