Related papers: Scalable Private Search with Wally
Query-based systems (QBSs) are one of the key approaches for sharing data. QBSs allow analysts to request aggregate information from a private protected dataset. Attacks are a crucial part of ensuring QBSs are truly privacy-preserving. The…
We design, to the best of our knowledge, the first differentially private (DP) stream aggregation processing system at scale. Our system -- Differential Privacy SQL Pipelines (DP-SQLP) -- is built using a streaming framework similar to…
Differentially private collaborative filtering is a challenging task, both in terms of accuracy and speed. We present a simple algorithm that is provably differentially private, while offering good performance, using a novel connection of…
While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data.…
Federal administrative data, such as tax data, are invaluable for research, but because of privacy concerns, access to these data is typically limited to select agencies and a few individuals. An alternative to sharing microlevel data is to…
Private selection mechanisms (e.g., Report Noisy Max, Sparse Vector) are fundamental primitives of differentially private (DP) data analysis with wide applications to private query release, voting, and hyperparameter tuning. Recent work…
A symmetric searchable encryption (SSE) scheme allows a client (data owner) to search on encrypted data outsourced to an untrusted cloud server. The search may either be a single keyword search or a complex query search like conjunctive or…
The need for a privacy management layer in today's systems started to manifest with the emergence of new systems for privacy-preserving analytics and privacy compliance. As a result, many independent efforts have emerged that try to provide…
In modern datasets, where single records can have multiple owners, enforcing user-level differential privacy requires capping each user's total contribution. This "contribution bounding" becomes a significant combinatorial challenge.…
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more…
To derive valuable insights from statistics, machine learning applications frequently analyze substantial amounts of data. In this work, we address the problem of designing efficient secure techniques to probe large datasets which allow a…
In-home IoT devices play a major role in healthcare systems as smart personal assistants. They usually come with a voice-enabled feature to add an extra level of usability and convenience to elderly, disabled people, and patients. In this…
We introduce a refined differentially private (DP) data structure for kernel density estimation (KDE), offering not only improved privacy-utility tradeoff but also better efficiency over prior results. Specifically, we study the…
The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…
Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users…
Differential privacy is fast becoming the gold standard in enabling statistical analysis of data while protecting the privacy of individuals. However, practical use of differential privacy still lags behind research progress because…
Differential privacy (DP) is widely employed to provide privacy protection for individuals by limiting information leakage from the aggregated data. Two well-known models of DP are the central model and the local model. The former requires…
Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the local model weights are shared among the clients for local…
Numerous studies have underscored the significant privacy risks associated with various leakage patterns in encrypted data stores. While many solutions have been proposed to mitigate these leakages, they either (1) incur substantial…
We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated…