AI RESEARCH
Differentially Private Datastore Generation for Retrieval-Augmented Inference
arXiv CS.LG
•
ArXi:2606.01413v1 Announce Type: cross It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datas without compromising individual privacy. This can be achieved using Differential Privacy (DP), which provides a formal guarantee that ensures individual contributions remain indistinguishable, even under adversarial analysis. In this paper, we