Differential privacy of cross-attention with provable guarantee
Cross-attention has become a fundamental module nowadays in many important artificial
intelligence applications, eg, retrieval-augmented generation (RAG), system prompt, guided …
intelligence applications, eg, retrieval-augmented generation (RAG), system prompt, guided …
A unifying framework for differentially private sums under continual observation
We study the problem of maintaining a differentially private decaying sum under continual
observation. We give a unifying framework and an efficient algorithm for this problem for any …
observation. We give a unifying framework and an efficient algorithm for this problem for any …
Differential privacy mechanisms in neural tangent kernel regression
Training data privacy is a fundamental problem in modern Artificial Intelligence (AI)
applications, such as face recognition, recommendation systems, language generation, and …
applications, such as face recognition, recommendation systems, language generation, and …
Differentially Private Hierarchical Heavy Hitters
The task of finding Hierarchical Heavy Hitters (HHH) was introduced by Cormode et al.[12]
as a generalisation of the heavy hitter problem. While finding HHH in data streams has been …
as a generalisation of the heavy hitter problem. While finding HHH in data streams has been …
Concurrent shuffle differential privacy under continual observation
We introduce the concurrent shuffle model of differential privacy. In this model we have
multiple concurrent shufflers permuting messages from different, possibly overlapping …
multiple concurrent shufflers permuting messages from different, possibly overlapping …
Differentially Private Substring and Document Counting
Differential privacy is the gold standard for privacy in data analysis. In many data analysis
applications, the data is a database of documents. For databases consisting of many …
applications, the data is a database of documents. For databases consisting of many …