Related papers: Context-aware Data Aggregation with Localized Info…

Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective…

Local differential privacy (LDP) is a variant of differential privacy (DP) that avoids the need for a trusted central curator, at the cost of a worse trade-off between privacy and utility. The shuffle model is a way to provide greater…

Stream data from real-time distributed systems such as IoT, tele-health, and crowdsourcing has become an important data source. However, the collection and analysis of user-generated stream data raise privacy concerns due to the potential…

Local differential privacy (LDP) has emerged as a promising paradigm for privacy-preserving data collection in distributed systems, where users contribute multi-dimensional records with potentially correlated attributes. Recent work has…

Image data has been greatly produced by individuals and commercial vendors in the daily life, and it has been used across various domains, like advertising, medical and traffic analysis. Recently, image data also appears to be greatly…

As machine learning (ML) becomes more prevalent in human-centric applications, there is a growing emphasis on algorithmic fairness and privacy protection. While previous research has explored these areas as separate objectives, there is a…

Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. However, LDP applies uniform protection to all data features, including less sensitive ones, which degrades performance of…

Estimating frequencies of certain items among a population is a basic step in data analytics, which enables more advanced data analytics (e.g., heavy hitter identification, frequent pattern mining), client software optimization, and…

Detecting personally identifiable information (PII) in user queries is critical for ensuring privacy in question-answering systems. Current approaches mainly redact all PII, disregarding the fact that some of them may be contextually…

Local differential privacy (LDP) enables private data sharing and analytics without the need for a trusted data collector. Error-optimal primitives (for, e.g., estimating means and item frequencies) under LDP have been well studied. For…

Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data…

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem…

LDP (Local Differential Privacy) has recently attracted much attention as a metric of data privacy that prevents the inference of personal data from obfuscated data in the local model. However, there are scenarios in which the adversary…

Local Differential Privacy protocols are stochastic protocols used in data aggregation when individual users do not trust the data aggregator with their private data. In such protocols there is a fundamental tradeoff between user privacy…

Federated heavy hitter analytics enables service providers to better understand the preferences of cross-party users by analyzing the most frequent items. As with federated learning, it faces challenges of privacy concerns, statistical…

Differentially private in-context learning (DP-ICL) has recently become an active research topic due to the inherent privacy risks of in-context learning. However, existing approaches overlook a critical component of modern large language…

In the modern digital world, a user of a smart system remains surrounded with as well as observed by a number of tiny IoT devices round the clock almost everywhere. Unfortunately, the ability of these devices to sense and share various…

Federated learning (FL), as a type of collaborative machine learning framework, is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. Nevertheless, from a viewpoint of information…

Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others. Obtaining text representations or embeddings using these…

Large language models are exposed to risks of extraction, distillation, and unauthorized fine-tuning. Existing defenses use watermarking or monitoring, but these act after leakage. We design AlignDP, a hybrid privacy lock that blocks…