3 accepted papers
Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interaction. Motivated by participation privacy, we study single-edit neighboring user streams, where one insertion/deletion shifts all subsequent updates an…
Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as the fundamental unit. However, existing methods still lack strong theoretical guarantees of robustness, and reject-sampl…
We propose a new private Approximate Nearest Neighbor (ANN) search scheme named Pacmann that allows a client to perform ANN search in a vector database without revealing the query vector to the server. Unlike prior constructions that run encrypted search on the server side, Pacmann carefully offloa…