Related papers: Decomposition-Based Optimal Bounds for Privacy Amp…
In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the parameters at the clients side before aggregating,…
Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-identification, attribute inference, and data reconstruction --…
Differential Privacy (DP) has become the gold standard for protecting individual privacy in data analytics, and the shuffle-DP model has attracted significant attention from both academia and industry due to its favorable balance between…
Recent research in differential privacy demonstrated that (sub)sampling can amplify the level of protection. For example, for $\epsilon$-differential privacy and simple random sampling with sampling rate $r$, the actual privacy guarantee is…
Differential privacy (DP) has been recently introduced to linear contextual bandits to formally address the privacy concerns in its associated personalized services to participating users (e.g., recommendations). Prior work largely focus on…
Spectral clustering is a widely used algorithm to find clusters in networks. Several researchers have studied the stability of spectral clustering under local differential privacy with the additional assumption that the underlying networks…
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is…
Secure aggregation is a foundational building block of privacy-preserving learning, yet achieving robustness under adversarial behavior remains challenging. Modern systems increasingly adopt the shuffle model of differential privacy…
Compressing the output of \epsilon-locally differentially private (LDP) randomizers naively leads to suboptimal utility. In this work, we demonstrate the benefits of using schemes that jointly compress and privatize the data using shared…
The privacy funnel (PF) gives a framework of privacy-preserving data release, where the goal is to release useful data while also limiting the exposure of associated sensitive information. This framework has garnered significant interest…
Metric Differential Privacy (mDP) extends the concept of Differential Privacy (DP) to serve as a new paradigm of data perturbation. It is designed to protect secret data represented in general metric space, such as text data encoded as word…
Recently, big data has seen explosive growth in the Internet of Things (IoT). Multi-layer FL (MFL) based on cloud-edge-end architecture can promote model training efficiency and model accuracy while preserving IoT data privacy. This paper…
A privacy-utility tradeoff is developed for an arbitrary set of finite-alphabet source distributions. Privacy is quantified using differential privacy (DP), and utility is quantified using expected Hamming distortion maximized over the set…
The Differential Privacy (DP) literature often centers on meeting privacy constraints by introducing noise to the query, typically using a pre-specified parametric distribution model with one or two degrees of freedom. However, this…
Duplicate records pose significant challenges in customer relationship management (CRM)and healthcare, often leading to inaccuracies in analytics, impaired user experiences, and compliance risks. Traditional deduplication methods rely…
Metric Differential Privacy (mDP) generalizes Local Differential Privacy (LDP) by adapting privacy guarantees based on pairwise distances, enabling context-aware protection and improved utility. While existing optimization-based methods…
Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…
Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…
Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially regarding scalability…
Federated learning (FL), a novel branch of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, it is still possible to access the model updates (gradient…