Related papers: RecPS: Privacy Risk Scoring for Recommender System…

The recommendation of points of interest (POIs) is essential in location-based social networks. It makes it easier for users and locations to share information. Recently, researchers tend to recommend POIs by treating them as large-scale…

Taking part in surveys, experiments, and studies is often compensated by rewards to increase the number of participants and encourage attendance. While privacy requirements are usually considered for participation, privacy aspects of the…

Large Language Models (LLMs) pose significant privacy risks, potentially leaking training data due to implicit memorization. Existing privacy attacks primarily focus on membership inference attacks (MIAs) or data extraction attacks, but…

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

Privacy risk assessments aim to analyze and quantify the privacy risks associated with new systems. As such, they are critically important in ensuring that adequate privacy protections are built in. However, current methods to quantify…

Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation…

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the…

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…

As large-scale models such as Large Language Models (LLMs) and Large Multimodal Models (LMMs) see increasing deployment, their privacy risks remain underexplored. Membership Inference Attacks (MIAs), which reveal whether a data point was…

Many studies in recommender systems (RecSys) adopt a general problem definition, i.e., to recommend preferred items to users based on past interactions. Such abstraction often lacks the domain-specific nuances necessary for practical…

Building a recommendation system involves analyzing user data, which can potentially leak sensitive information about users. Anonymizing user data is often not sufficient for preserving user privacy. Motivated by this, we propose a…

Website owners make conscious and unconscious decisions that affect their users, potentially exposing them to privacy and security risks in the process. In this paper we introduce PrivacyScore, an automated website scanning portal that…

With increasing frequency of high-profile privacy breaches in various online platforms, users are becoming more concerned about their privacy. And recommender system is the core component of online platforms for providing personalized…

Machine learning models, in particular deep neural networks, are currently an integral part of various applications, from healthcare to finance. However, using sensitive data to train these models raises concerns about privacy and security.…

Cross-domain sequential recommendation is an important development direction of recommender systems. It combines the characteristics of sequential recommender systems and cross-domain recommender systems, which can capture the dynamic…

Membership inference attacks aim to detect if a particular data point was used in training a model. We design a novel statistical test to perform robust membership inference attacks (RMIA) with low computational overhead. We achieve this by…

Collaborative-learning-based recommender systems, such as those employing Federated Learning (FL) and Gossip Learning (GL), allow users to train models while keeping their history of liked items on their devices. While these methods were…

There exist situations of decision-making under information overload in the Internet, where people have an overwhelming number of available options to choose from, e.g. products to buy in an e-commerce site, or restaurants to visit in a…

Recommender systems (RecSys) are widely used across various modern digital platforms and have garnered significant attention. Traditional recommender systems usually focus only on fixed and simple recommendation scenarios, making it…

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…