相关论文: Privacy Auditing with Zero (0) Training Run

Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations…

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…

Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensive research on each problem individually, their intersection…

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…

A number of learning models used in consequential domains, such as to assist in legal, banking, hiring, and healthcare decisions, make use of potentially sensitive users' information to carry out inference. Further, the complete set of…

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…

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…

Recently issued data privacy regulations like GDPR (General Data Protection Regulation) grant individuals the right to be forgotten. In the context of machine learning, this requires a model to forget about a training data sample if…

Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about…

We consider training machine learning models using Training data located on multiple private and geographically-scattered servers with different privacy settings. Due to the distributed nature of the data, communicating with all…

In settings like vaccination registries, individuals act after observing others, and the resulting public records can expose private information. We study privacy-preserving sequential learning, where agents add endogenous noise to their…

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…

Differentially private (DP) optimization has been widely adopted as a standard approach to provide rigorous privacy guarantees for training datasets. DP auditing verifies whether a model trained with DP optimization satisfies its claimed…

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

This paper introduces a novel theoretical framework for auditing differential privacy (DP) in a black-box setting. Leveraging the concept of $f$-differential privacy, we explicitly define type I and type II errors and propose an auditing…

Differential privacy is the state-of-the-art definition for privacy, guaranteeing that any analysis performed on a sensitive dataset leaks no information about the individuals whose data are contained therein. In this thesis, we develop…

Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data…

Membership inference (MI) attack is currently the most popular test for measuring privacy leakage in machine learning models. Given a machine learning model, a data point and some auxiliary information, the goal of an MI attack is to…

Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…