相关论文: PrivateFetch: Scalable Catalog Delivery in Privacy…
Differential privacy (DP) allows data analysts to query databases that contain users' sensitive information while providing a quantifiable privacy guarantee to users. Recent interactive DP systems such as APEx provide accuracy guarantees…
Major advertising platforms recently increased privacy protections by limiting advertisers' access to individual-level data. Instead of providing access to granular raw data, the platforms only allow a limited number of aggregate queries to…
When analysing Differentially Private (DP) machine learning pipelines, the potential privacy cost of data-dependent pre-processing is frequently overlooked in privacy accounting. In this work, we propose a general framework to evaluate the…
How to preserve users' privacy while supporting high-utility analytics for low-latency stream processing? To answer this question: we describe the design, implementation, and evaluation of PRIVAPPROX, a data analytics system for…
Modern high-performance architectures employ large last-level caches (LLCs). While large LLCs can reduce average memory access latency for workloads with a high degree of locality, they can also increase latency for workloads with irregular…
To mitigate privacy leakage and performance issues in personalized advertising, this paper proposes a framework that integrates federated learning and differential privacy. The system combines distributed feature extraction, dynamic privacy…
Communication complexity and privacy are the two key challenges in Federated Learning where the goal is to perform a distributed learning through a large volume of devices. In this work, we introduce FedSKETCH and FedSKETCHGATE algorithms…
Online advertising fuels the (seemingly) free internet. However, although users can access most of the web services free of charge, they pay a heavy coston their privacy. They are forced to trust third parties and intermediaries, who not…
Privacy and security have rapidly emerged as first order design constraints. Users now demand more protection over who can see their data (confidentiality) as well as how it is used (control). Here, existing cryptographic techniques for…
A large fraction of online display advertising is sold via guaranteed contracts: a publisher guarantees to the advertiser a certain number of user visits satisfying the targeting predicates of the contract. The publisher is then tasked with…
We introduce the linear-transformation model, a distributed model of differentially private data analysis. Clients have access to a trusted platform capable of applying a public matrix to their inputs. Such computations can be securely…
In Federated Learning (FL), accessing private client data incurs communication and privacy costs. As a result, FL deployments commonly prefinetune pretrained foundation models on a (large, possibly public) dataset that is held by the…
The Internet of Things (IoT) devices, such as smart speakers can collect sensitive user data, necessitating the need for users to manage their privacy preferences. However, configuring these preferences presents users with multiple…
Increasingly large trip demands have strained urban transportation capacity, which consequently leads to traffic congestion and rapid growth of greenhouse gas emissions. In this work, we focus on achieving sustainable transportation by…
Today, targeted online advertising relies on unique identifiers assigned to users through third-party cookies--a practice at odds with user privacy. While the web and advertising communities have proposed solutions that we refer to as…
We propose $\mathtt{PrivHP}$, a lightweight synthetic data generator with \textit{differential privacy} guarantees. $\mathtt{PrivHP}$ uses a novel hierarchical decomposition that approximates the input's cumulative distribution function…
End users face a choice between privacy and efficiency in current Large Language Model (LLM) service paradigms. In cloud-based paradigms, users are forced to compromise data locality for generation quality and processing speed. Conversely,…
In distributed computing environments, collaborative machine learning enables multiple clients to train a global model collaboratively. To preserve privacy in such settings, a common technique is to utilize frequent updates and…
Evaluating the usefulness of data before purchase is essential when obtaining data for high-quality machine learning models, yet both model builders and data providers are often unwilling to reveal their proprietary assets. We present…
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…