Confidential — Stefan Michaelcheck Only

Addressing Memorization and Aggregation Risks in AI: A Knowledge Graph Approach to Privacy

2026formal foundationsnovelframework

Jinhui Zuo

Applied Sciences

https://doi.org/10.3390/app16041796OpenAlex: W7128601479
4
URLs Found
0
Internal Citations
1
Authors
usable
Abstract Quality
GPT-5.5 Abstract Analysis

Problems Identified (5)

AI memorization privacy risk: AI models can memorize specific records, which can expose sensitive data through model access.

Context-dependent privacy risk modeling gap: Current privacy-enhancing technologies often fail to account for context-dependent privacy risks arising from relationships and interactions between data records.

Private data aggregation risk: Relationships, redundancy, and interactions between data records can create high privacy risks through memorization and data aggregation.

AI memorization privacy risk: AI models can memorize specific records, which can expose sensitive data through model access.

Context-dependent privacy risk modeling gap: Current privacy-enhancing technologies often fail to account for context-dependent privacy risks arising from relationships and interactions between data records.

Proposed Solutions (5)

PrivGraph knowledge graph: PrivGraph is a hierarchically structured knowledge graph for modeling and aggregating private information.

Sensitivity Level Factor: The Sensitivity Level Factor quantifies how much an individual’s private information is embedded in the data.

PrivGraph knowledge probing: A PrivGraph-based knowledge probing method is proposed for post-training privacy assessments.

Lifecycle privacy integration: PrivGraph is discussed as part of the AI engineering lifecycle for traceable full-spectrum privacy protection.

PrivGraph knowledge graph: PrivGraph is a hierarchically structured knowledge graph for modeling and aggregating private information.

Results (3)

Subtle private-link learning observed:

Comparable PII detection performance:

Effective private aggregation modeling:

Research Domain

AI privacy and privacy-preserving technologies

← Back to all papers