Related papers: A Statistical Threshold for Adversarial Classifica…
Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…
The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines. As the evolution of sophisticated Membership Inference Attacks (MIAs) threatens the secrecy…
In an MPC-protected distributed computation, although the use of MPC assures data privacy during computation, sensitive information may still be inferred by curious MPC participants from the computation output. This can be observed, for…
This paper adopts Arimoto's $\alpha$-Mutual Information as a tunable privacy measure, in a privacy-preserving data release setting that aims to prevent disclosing private data to adversaries. By fine-tuning the privacy metric, we…
Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off…
We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. Their conceptual similarity was first observed by Dwork and…
Differential Privacy (DP) provides tight upper bounds on the capabilities of optimal adversaries, but such adversaries are rarely encountered in practice. Under the hypothesis testing/membership inference interpretation of DP, we examine…
Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even…
Artificial Intelligence systems require a through assessment of different pillars of trust, namely, fairness, interpretability, data and model privacy, reliability (safety) and robustness against against adversarial attacks. While these…
Numerous generalization techniques have been proposed for privacy preserving data publishing. Most existing techniques, however, implicitly assume that the adversary knows little about the anonymization algorithm adopted by the data…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…
We consider the setting where a user with sensitive features wishes to obtain a recommendation from a server in a differentially private fashion. We propose a ``multi-selection'' architecture where the server can send back multiple…
Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zhang et al. VLDB 2012) for training linear regression models…
We study privacy-utility trade-offs where users share privacy-correlated useful information with a service provider to obtain some utility. The service provider is adversarial in the sense that it can infer the users' private information…
We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models. Previous research has demonstrated that differential privacy (DP)…
We introduce a privacy measure called statistic maximal leakage that quantifies how much a privacy mechanism leaks about a specific secret, relative to the adversary's prior information about that secret. Statistic maximal leakage is an…
Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder their adoption in high-stake applications. Thus, it is essential to…
We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample…
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…
The growing number of adversarial attacks in recent years gives attackers an advantage over defenders, as defenders must train detectors after knowing the types of attacks, and many models need to be maintained to ensure good performance in…