Related papers: A Note On Interpreting Canary Exposure

Ensuring the privacy of training data is a growing concern since many machine learning models are trained on confidential and potentially sensitive data. Much attention has been devoted to methods for protecting individual privacy during…

Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…

In statistical disclosure control, the goal of data analysis is twofold: The released information must provide accurate and useful statistics about the underlying population of interest, while minimizing the potential for an individual…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.…

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive---new systems and models are being deployed in every…

In this paper we consider the setting where machine learning models are retrained on updated datasets in order to incorporate the most up-to-date information or reflect distribution shifts. We investigate whether one can infer information…

Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models. To this end, we take a novel look at black box interpretation of test predictions in terms of training examples.…

Prior approaches for membership privacy preservation usually update or retrain all weights in neural networks, which is costly and can lead to unnecessary utility loss or even more serious misalignment in predictions between training data…

The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often…

Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this…

Privacy definitions provide ways for trading-off the privacy of individuals in a statistical database for the utility of downstream analysis of the data. In this paper, we present Blowfish, a class of privacy definitions inspired by the…

The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both research and industry. Considering the resource-intensive nature…

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…

Credit risk modeling has permeated our everyday life. Most banks and financial companies use this technique to model their clients' trustworthiness. While machine learning is increasingly used in this field, the resulting large-scale…

Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leakage using abductive explanations, which identifies minimal…

Recently, an increasing number of laws have governed the useability of users' privacy. For example, Article 17 of the General Data Protection Regulation (GDPR), the right to be forgotten, requires machine learning applications to remove a…

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…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…