Joann Chen
San Diego State University, CA·Computer Science
Data provenance is a record of where data came from, who created it, and how it was used and changed. These records help organizations check data integrity, run security audits and follow privacy rules in healthcare, finance and government.
- Fields
Computer Science
Mathematics & Statistics
- Topics
differential privacy
data provenance
provenance graphs
- Grants
- 1 known grant, through Sep 2027
What they work on
- Identify privacy risks in provenance-based machine learning anomaly detectors by applying property inference, membership inference and graph reconstruction attacks to them.
- Develop snapshot-level differential privacy for provenance graphs, a way of adding mathematical privacy protection whose guarantees match enterprise privacy policies, compliance requirements and performance needs.
- Design a subgraph synthesis method that generates differentially private synthetic provenance graphs while handling the dense correlations and large scale of real provenance data.
More about the research
Provenance is often stored as a graph, a network of linked events and data items. Detailed provenance graphs, however, can reveal sensitive information and can be attacked. Differential privacy is a mathematical method that limits how much any single person's data affects an analysis's results. It protects even against attackers who know a lot, but in practice it is hard to keep data useful while keeping it private.
Why it matters
Hospitals, banks and public safety agencies keep detailed data activity records for audits and regulatory compliance, but those records can expose sensitive information. Practical differential privacy for provenance graphs could let these organizations keep using provenance for security monitoring while lowering privacy risks. Privacy-preserving synthetic datasets could also be shared more safely.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Zeyu Ding
Binghamton University, NY·Computer Science
Build automated tools that analyze an SQL database schema and help users interactively define a customizable privacy model specifying which data elements need differential-privacy protection, and which variant.
Guang Wang
Florida State University, FL·Computer Science
Build cross-domain data curation tools for MobilityNet that combine real mobility datasets from different sources to reduce data bias.
Assefaw Gebremedhin
Washington State University, WA·Computer Science
Develop robust and trustworthy machine learning algorithms with anomaly-detection features that flag malicious activity in AI systems used in healthcare, autonomous vehicles and smart cities.
The school
San Diego State University: 13 labs on PI Pages, $182M a year on research, 142 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.