Related papers: DeSIA: Attribute Inference Attacks Against Limited…
Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…
In recent years, recommender systems are crucially important for the delivery of personalized services that satisfy users' preferences. With personalized recommendation services, users can enjoy a variety of recommendations such as movies,…
We propose new privacy attacks to infer attributes (e.g., locations, occupations, and interests) of online social network users. Our attacks leverage seemingly innocent user information that is publicly available in online social networks…
Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still substantial room for improvement in the privacy-utility…
Federated learning systems are increasingly threatened by data poisoning attacks, where malicious clients compromise global models by contributing tampered updates. Existing defenses often rely on impractical assumptions, such as access to…
Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their…
Aggregate location data is often used to support smart services and applications, e.g., generating live traffic maps or predicting visits to businesses. In this paper, we present the first study on the feasibility of membership inference…
The prosperity of machine learning has also brought people's concerns about data privacy. Among them, inference attacks can implement privacy breaches in various MLaaS scenarios and model training/prediction phases. Specifically, inference…
We describe and evaluate an attack that reconstructs the histogram of any target attribute of a sensitive dataset which can only be queried through a specific class of real-world privacy-preserving algorithms which we call bounded…
The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing…
Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…
Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data.…
Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data…
Federated Learning (FL) offers a promising framework for collaboratively training machine learning models across decentralized genomic datasets without direct data sharing. While this approach preserves data locality, it remains susceptible…
Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is…
In contrast to prevalent Federated Learning (FL) privacy inference techniques such as generative adversarial networks attacks, membership inference attacks, property inference attacks, and model inversion attacks, we devise an innovative…
Privacy-preserving computing is crucial for multi-center machine learning in many applications such as healthcare and finance. In this paper a Multi-center Privacy Computing framework with Predictions Aggregation (MPCPA) based on denoising…
Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit…
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…
Anonymized data is highly valuable to both businesses and researchers. A large body of research has however shown the strong limits of the de-identification release-and-forget model, where data is anonymized and shared. This has led to the…