Related papers: Defending Membership Inference Attacks via Privacy…
Neural networks are susceptible to data inference attacks such as the membership inference attack, the adversarial model inversion attack and the attribute inference attack, where the attacker could infer useful information such as the…
We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive…
Authentication systems are vulnerable to model inversion attacks where an adversary is able to approximate the inverse of a target machine learning model. Biometric models are a prime candidate for this type of attack. This is because…
Machine learning models have recently enjoyed a significant increase in size and popularity. However, this growth has created concerns about dataset privacy. To counteract data leakage, various privacy frameworks guarantee that the output…
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…
Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a…
Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model, offering a practical alternative to full retraining. However, it introduces privacy risks: an adversary with access to…
Feature selection is one of the most decisive tools in understanding data and machine learning models. Among other methods, sparsity induced by $L^{1}$ penalty is one of the simplest and best studied approaches to this problem. Although…
With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…
Neural networks are usually not the tool of choice for nonparametric high-dimensional problems where the number of input features is much larger than the number of observations. Though neural networks can approximate complex multivariate…
High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e.g. personalized medicine), where high dimensional features (e.g. genomic data) on the users are available, but only a small subset…
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…
Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…
Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training…
Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data scientists and machine learning engineers seek to use…
Membership inference attacks have emerged as a significant privacy concern in the training of deep learning models, where attackers can infer whether a data point was part of the training set based on the model's outputs. To address this…
The vulnerability of machine learning models to membership inference attacks has received much attention in recent years. However, existing attacks mostly remain impractical due to having high false positive rates, where non-member samples…
Modern machine learning models are increasingly deployed behind APIs. This renders standard weight-privatization methods (e.g. DP-SGD) unnecessarily noisy at the cost of utility. While model weights may vary significantly across training…
Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…
We propose a general statistical inference framework to capture the privacy threat incurred by a user that releases data to a passive but curious adversary, given utility constraints. We show that applying this general framework to the…