Related papers: Exploit the Leak: Understanding Risks in Biometric…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry. However, most existing methods have their limitations in practical applications. On the…

As digital data transmission continues to scale, concerns about privacy grow increasingly urgent - yet privacy remains a socially constructed and ambiguously defined concept, lacking a universally accepted quantitative measure. This work…

We investigate an attack on a machine learning model that predicts whether a person or household will relocate in the next two years, i.e., a propensity-to-move classifier. The attack assumes that the attacker can query the model to obtain…

Recent developments in cloud storage architectures have originated new models of online storage as cooperative storage systems and interconnected clouds. Such distributed environments involve many organizations, thus ensuring…

Biometric recognition is a highly adopted technology to support different kinds of applications, ranging from security and access control applications to low enforcement applications. However, such systems raise serious privacy and data…

Encrypted search schemes have been proposed to address growing privacy concerns. However, several leakage-abuse attacks have highlighted some security vulnerabilities. Recent attacks assumed an attacker's knowledge containing data…

Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…

Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of catering this requirement. However,…

In this paper, we study the probability of successful deception of an uncompressed biometric authentication system with side information at the adversary. It represents the scenario where the adversary may have correlated side information,…

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information…

When users make personal privacy choices, correlation between their data can cause inadvertent leakage about users who do not want to share their data by other users sharing their data. As a solution, we consider local redaction mechanisms.…

Side channels represent a broad class of security vulnerabilities that have been demonstrated to exist in many applications. Because completely eliminating side channels often leads to prohibitively high overhead, there is a need for a…

Most methods for publishing data with privacy guarantees introduce randomness into datasets which reduces the utility of the published data. In this paper, we study the privacy-utility tradeoff by taking maximal leakage as the privacy…

A basic model for key agreement with biometric or physical identifiers is extended to include measurements of a hidden source through a general broadcast channel (BC). An inner bound for strong secrecy, maximum key rate, and minimum…

Synthetic data are an attractive concept to enable privacy in data sharing. A fundamental question is how similar the privacy-preserving synthetic data are compared to the true data. Using metric privacy, an effective generalization of…

AI-based talking-head videoconferencing systems reduce bandwidth by sending a compact pose-expression latent and re-synthesizing RGB at the receiver, but this latent can be puppeteered, letting an attacker hijack a victim's likeness in real…

For the safe sharing pre-trained language models, no guidelines exist at present owing to the difficulty in estimating the upper bound of the risk of privacy leakage. One problem is that previous studies have assessed the risk for different…

To analyze the privacy guarantee of personal data in a database that is subject to queries it is necessary to model the prior knowledge of a possible attacker. Differential privacy considers a worst-case scenario where he knows almost…