Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies
Researchers have developed a framework to identify and mitigate privacy risks in knowledge graph embeddings (KGEs). The study demonstrates how adversaries can infer sensitive user attributes from KGE outputs, even when this information is not explicitly stored. The proposed defense mechanism involves post-processing KGE results to sanitize them, balancing recommendation quality with enhanced privacy protection. AI
IMPACT This research highlights potential privacy vulnerabilities in knowledge graph embeddings, prompting the development of new defense strategies to protect sensitive user data.