Keke Chen
Northwestern Mutual Associate Professor
Department of Computer Science
Northwestern Mutual Data Science Institute
Marquette University
Office: Cudahy Hall 380
Phone: 414-288-3230 (office)
LinkedIn: https://www.linkedin.com/in/keke-chen-29b5bb2/
Email: keke.chen AT marquette . edu
ShortBio: I got my PhD in Computer Science from Georgia Tech and have been working in both industry (Yahoo! Labs) and academia.
I am looking for highly motivated students who are interested in AI, security and privacy, data science, and distributed computing. Our graduates have joined Meta, TikTok, Google, HP, Amazon, IBM, etc.
What's New
Collaboration on small-scale machine learning models on cancer-detection devices: Allison Scarbrough, Keke Chen, Bing Yu, "Designing a use-error robust machine learning model for quantitative analysis of diffuse reflectance spectra", to appear in the Journal of Biomedical Optics, 2024
TEE for confidential graph mining in the cloud: Mubashwir Alam and Keke Chen, "TEE-Graph: efficient privacy and ownership protection for cloud-based graph spectral analysis", to appear in Frontiers in Big Data, 2023
Demos on image disguising methods (CCS23) and TEE-MR (ICDCS23). Check the links
Developing oblivious solutions for Trusted Execution Environments to improve the resilience to side-channel attacks: "Making Your Program Oblivious: a Comparative Study for Side-channel-safe Confidential Computing" to appear in CLOUD 2023.
"GAN-Based Domain Inference Attack" is a new attack designed to enhance model-targeted attacks, such as model inversion attacks and membership inference attacks. It helps identify the most relevant domains for a target model if the attacker has no prior domain knowledge. It will appear in AAAI 2023. Congratulations, Yuechun (Ethan) Gu!
Glad to be a part of the CyberWIN team for the first "NSF CyberCorps Scholarship for Service" award in Wisconsin. The project will start in 1/2023.
Thanks to the NSF CICI program for supporting our project "Confidential Computing in Reproducible Collaborative Workflows" starting in 1/2023!
Challenges for applying TEEs in cloud HPC to appear in IEEE Internet Computing, https://arxiv.org/abs/2212.02378, 2022
SGX-MR and DisguisedNets prototypes will be available in 2022. Please email keke.chen@marquette.edu for details.
A new paper about the application of scalable methods for hierarchical clustering in B cell clonality analysis, to appear in IEEE BigData 2021. This is a collaborative effort with the Jiang Lab at the University of Pennsylvania, ImmuDX LLC, and XC Bioanalytics.
The enhanced version of image disguising for outsourced deep learning, by Sagar Sharma, Mubashwir, and Keke Chen, published in IEEE CLOUD 2021.
When SGX-based secure programs are used for processing encrypted data, access pattern leakage can still be explored to learn sensitive information. We propose that by regulating application-level data flows with a MapReduce-style processing model, we can protect access patterns more efficiently - "SGX-MR: Regulating Dataflows for Protecting Access Patterns of Data-Intensive SGX Applications" by Mubashwir Alam, Sagar Sharma, and Keke Chen, to appear in Privacy Enhancing Technologies Symposium, 2021
To find crypto-friendly learning algorithms for confidential learning - Sagar Sharma and Keke Chen "Confidential Boosting with Random Linear Classifiers for Outsourced User-generated Data", to appear in the European Symposium on Research in Computer Security (ESORICS), 2019
To appear in ICWSM19, "Who should be the captain this week? Leveraging inferred diversity-enhanced crowd wisdom for a Fantasy Premier League prediction task" by Shreyansh Bhatt, Keke Chen, Valerie L. Shalin, Amit Sheth, Brandon Minnery. This is a collaborative work on optimizing the crowd composition to achieve the wisdom of crowd without the crowd's prior performance data.
I am co-chairing BigData Congress 2019. Welcome to submit papers. The deadline is March 22, 2019 for all tracks.
Serving on the editorial board of ACM Transactions on Internet Technology (TOIT), starting in 2019
"Knowledge graph enhanced community detection and characterization" to appear in ACM Web Search and Data Mining (WSDM) 2019, by Shreyansh Bhatt, Swati Padhee, Keke Chen, Valerie Shalin, Derek Doran, Amit Sheth and Brandon Minnery.
Two posters about privacy-preserving deep learning and boosting in ACM CCS 2018, both led by Sagar Sharma.
Sagar Sharma, James Powers, and Keke Chen "PrivateGraph: Privacy-Preserving Spectral Analysis of Encrypted Graphs in the Cloud ", IEEE TKDE, 2018. It includes a comparative study on two provably secure solutions (Ring-LWE vs. Additive HE + novel data obscuration methods) for graph spectral analysis in the cloud, where encrypted graphs are possibly contributed by millions of users.
A summary about the issues with privacy-preserving data analytics for IoT/Cloud based healthcare systems, by Sagar Sharma, Keke Chen, and Amit Sheth, to appear in IEEE Internet Computing, 2018.