相关论文: PrivateFetch: Scalable Catalog Delivery in Privacy…

With the rapid development of applications in open distributed environments such as eCommerce, privacy of information is becoming a critical issue. Today, many online companies are gathering information and have assembled sophisticated…

Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD injects isotropic noise. Second-order preconditioning can resolve this, but estimating…

Online mobile advertising ecosystems provide advertising and analytics services that collect, aggregate, process, and trade a rich amount of consumers' personal data and carry out interest-based ad targeting, which raised serious privacy…

Sketches are widely used for frequency estimation of data with a large domain. However, sketches-based frequency estimation faces more challenges when considering privacy. Local differential privacy (LDP) is a solution to frequency…

Auditing algorithms' privacy typically involves simulating a game-based protocol that guesses which of two adjacent datasets was the original input. Traditional approaches require thousands of such simulations, leading to significant…

Predictive analytics is widely used in learning analytics, but many resource-constrained institutions lack the capacity to develop their own models or rely on proprietary ones trained in different contexts with little transparency. Transfer…

Privacy by Design (PbD) is the most common approach followed by software developers who aim to reduce risks within their application designs, yet it remains commonplace for developers to retain little conceptual understanding of what is…

When multiple parties that deal with private data aim for a collaborative prediction task such as medical image classification, they are often constrained by data protection regulations and lack of trust among collaborating parties. If done…

Ensuring the privacy of training data is a growing concern since many machine learning models are trained on confidential and potentially sensitive data. Much attention has been devoted to methods for protecting individual privacy during…

Privacy-Preserving Machine Learning as a Service (PP-MLaaS) enables secure neural network inference by integrating cryptographic primitives such as homomorphic encryption (HE) and multi-party computation (MPC), protecting both client data…

Unlike suggested during their early years of existence, Bitcoin and similar cryptocurrencies in fact offer significantly less privacy as compared to traditional banking. A myriad of privacy-enhancing extensions to those cryptocurrencies as…

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…

This paper focuses on designing a privacy-preserving Machine Learning (ML) inference protocol for a hierarchical setup, where clients own/generate data, model owners (cloud servers) have a pre-trained ML model, and edge servers perform ML…

Online advertising fuels the (seemingly) free internet. However, although users can access most websites free of charge, they need to pay a heavy cost on their privacy and blindly trust third parties and intermediaries that absorb great…

The ongoing deprecation of third-party cookies by web browser vendors has sparked the proposal of alternative methods to support more privacy-preserving personalized advertising on web browsers and applications. The Topics API is being…

We consider a system, containing a library of multiple files and a general memoryless communication network through which a server is connected to multiple users, each equipped with a local isolated cache of certain size that can be used to…

Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeoff between…

Organizational networks are vulnerable to traffic-analysis attacks that enable adversaries to infer sensitive information from the network traffic - even if encryption is used. Typical anonymous communication networks are tailored to the…

In the mobile Internet era, the recommender system has become an irreplaceable tool to help users discover useful items, and thus alleviating the information overload problem. Recent deep neural network (DNN)-based recommender system…

Privacy-preserving federated graph analytics is an emerging area of research. The goal is to run graph analytics queries over a set of devices that are organized as a graph while keeping the raw data on the devices rather than centralizing…