Related papers: Membership Inference Attacks Against Recommender S…
Recommender systems are commonly trained on centrally collected user interaction data like views or clicks. This practice however raises serious privacy concerns regarding the recommender's collection and handling of potentially sensitive…
It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…
The large language model (LLM) powered recommendation paradigm has been proposed to address the limitations of traditional recommender systems, which often struggle to handle cold start users or items with new IDs. Despite its…
Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…
When an adversary provides poison samples to a machine learning model, privacy leakage, such as membership inference attacks that infer whether a sample was included in the training of the model, becomes effective by moving the sample to an…
With the wide-spread application of machine learning models, it has become critical to study the potential data leakage of models trained on sensitive data. Recently, various membership inference (MI) attacks are proposed to determine if a…
Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's training set by conducting a membership inference attack…
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…
Recommender models are hard to evaluate, particularly under offline setting. In this paper, we provide a comprehensive and critical analysis of the data leakage issue in recommender system offline evaluation. Data leakage is caused by not…
Deep learning has attracted broad interest in healthcare and medical communities. However, there has been little research into the privacy issues created by deep networks trained for medical applications. Recently developed inference attack…
Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…
In collaborative recommendation systems, privacy may be compromised, as users' opinions are used to generate recommendations for others. In this paper, we consider an online collaborative recommendation system, and we measure users' privacy…
While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by…
Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data,…
Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…
Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing empirical privacy…
Information has exploded on the Internet and mobile with the advent of the big data era. In particular, recommendation systems are widely used to help consumers who struggle to select the best products among such a large amount of…
Privacy attacks on Machine Learning (ML) models often focus on inferring the existence of particular data points in the training data. However, what the adversary really wants to know is if a particular individual's (subject's) data was…
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…
With an increasing focus on data privacy, there have been pilot studies on recommender systems in a federated learning (FL) framework, where multiple parties collaboratively train a model without sharing their data. Most of these studies…