Related papers: AnonPSI: An Anonymity Assessment Framework for PSI

Biometric data is pervasively captured and analyzed. Using modern machine learning approaches, identity and attribute inferences attacks have proven high accuracy. Anonymizations aim to mitigate such disclosures by modifying data in a way…

The architectures of deployed anonymity systems such as Tor suffer from two key problems that limit user's trust in these systems. First, paths for anonymous communication are built without considering trust relationships between users and…

In this paper we analyze different biometric authentication protocols considering an internal adversary. Our contribution takes place at two levels. On the one hand, we introduce a new comprehensive framework that encompasses the various…

The explosion in volume and variety of data offers enormous potential for research and commercial use. Increased availability of personal data is of particular interest in enabling highly customised services tuned to individual needs.…

Stream-based communication dominates today's Internet, posing unique challenges for anonymous communication networks (ACNs). Traditionally designed for independent messages, ACNs struggle to account for the inherent vulnerabilities of…

This paper proposes Prism, a secret sharing based approach to compute private set operations (i.e., intersection and union), as well as aggregates over outsourced databases belonging to multiple owners. Prism enables data owners to pre-load…

In this work, we systematically explore the data privacy issues of dataset pruning in machine learning systems. Our findings reveal, for the first time, that even if data in the redundant set is solely used before model training, its…

Federated Learning lends itself as a promising paradigm in enabling distributed learning for autonomous vehicles applications and ensuring data privacy while enhancing and refining predictive model performance through collaborative training…

This work considers active deanonymization of bipartite networks. The scenario arises naturally in evaluating privacy in various applications such as social networks, mobility networks, and medical databases. For instance, in active…

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…

Spatially and temporally dense street imagery (DSI) datasets have grown unbounded. In 2024, individual companies possessed around 3 trillion unique images of public streets. DSI data streams are only set to grow as companies like Lyft and…

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership…

Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on…

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

We study a security problem for interconnected systems, where each subsystem aims to detect local attacks using local measurements and information exchanged with neighboring subsystems. The subsystems also wish to maintain the privacy of…

We introduce the Poisson Binomial mechanism (PBM), a discrete differential privacy mechanism for distributed mean estimation (DME) with applications to federated learning and analytics. We provide a tight analysis of its privacy guarantees,…

Federated Learning (FL) is an emerging machine learning paradigm that enables multiple parties to collaboratively train models without sharing raw data, ensuring data privacy. In Vertical FL (VFL), where each party holds different features…

Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users' membership…