Related papers: Measuring Information Leakage in Non-stochastic Br…

In a biometric authentication or identification system, the matcher compares a stored and a fresh template to determine whether there is a match. This assessment is based on both a similarity score and a predefined threshold. For better…

We consider a non-stochastic privacy-preserving problem in which an adversary aims to infer sensitive information $S$ from publicly accessible data $X$ without using statistics. We consider the problem of generating and releasing a…

We study the design of mechanisms -- e.g., auctions -- when the designer does not control information flows between mechanism participants. A mechanism equilibrium is leakage-proof if no player conditions their actions on leaked…

We study the problem of data disclosure with privacy guarantees, wherein the utility of the disclosed data is ensured via a \emph{hard distortion} constraint. Unlike average distortion, hard distortion provides a deterministic guarantee of…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

Adversarial examples, generated by carefully crafted perturbation, have attracted considerable attention in research fields. Recent works have argued that the existence of the robust and non-robust features is a primary cause of the…

Information disclosure can compromise privacy when revealed information is correlated with private information. We consider the notion of inferential privacy, which measures privacy leakage by bounding the inferential power a Bayesian…

Federated learning is an established method for training machine learning models without sharing training data. However, recent work has shown that it cannot guarantee data privacy as shared gradients can still leak sensitive information.…

Opacity is a general language-theoretic framework in which several security properties of a system can be expressed. Its parameters are a predicate, given as a subset of runs of the system, and an observation function, from the set of runs…

We introduce password strength information signaling as a novel, yet counter-intuitive, defense mechanism against password cracking attacks. Recent breaches have exposed billions of user passwords to the dangerous threat of offline password…

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

Quantitative information flow (QIF) is concerned with assessing the leakage of information in computational systems. In QIF there are two main perspectives for the quantification of leakage. On one hand, the static perspective considers all…

Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…

In September 2017, McAffee Labs quarterly report estimated that brute force attacks represent 20\% of total network attacks, making them the most prevalent type of attack ex-aequo with browser based vulnerabilities. These attacks have…

As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely…

Several mathematical ideas have been investigated for Quantitative Information Flow. Information theory, probability, guessability are the main ideas in most proposals. They aim to quantify how much information is leaked, how likely is to…

In 2011 Bhaskar et al. pointed out that in many cases one can ensure sufficient level of privacy without adding noise by utilizing adversarial uncertainty. Informally speaking, this observation comes from the fact that if at least a part of…

Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…

We introduce an analytical framework to quantify the changes in a machine learning algorithm's output distribution following the inclusion of a few data points in its training set, a notion we define as leave-one-out distinguishability…