Related papers: A Tunable Measure for Information Leakage

Information measures can be constructed from R\'enyi divergences much like mutual information from Kullback-Leibler divergence. One such information measure is known as Sibson $\alpha$-mutual information and has received renewed attention…

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data reconstruction attacks.…

A deterministic privacy metric using non-stochastic information theory is developed. Particularly, minimax information is used to construct a measure of information leakage, which is inversely proportional to the measure of privacy. Anyone…

In this work, we present an alternative to conventional residual connections, which is inspired by maxout nets. This means that instead of the addition in residual connections, our approach only propagates the maximum value or, in the leaky…

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…

The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the…

We consider a scenario in which an autonomous agent carries out a mission in a stochastic environment while passively observed by an adversary. For the agent, minimizing the information leaked to the adversary regarding its high-level…

Information-theoretic (IT) measures based on $f$-divergences have recently gained interest as a measure of privacy leakage as they allow for trading off privacy against utility using only a single-value characterization. However, their…

Redacted emails satisfy most privacy requirements but they make it more difficult to detect anomalous emails that may be indicative of data exfiltration. In this paper we develop an enhanced method of Active Learning using an information…

To maximize average information gain for a classical measurement, all outcomes of an observation must be equally likely. The condition of equally likely outcomes may be enforced in quantum theory by ensuring that one's state $\rho$ is…

This paper focuses on parameter estimation and introduces a new method for lower bounding the Bayesian risk. The method allows for the use of virtually \emph{any} information measure, including R\'enyi's $\alpha$, $\varphi$-Divergences, and…

Underestimating the leakage can compromise secrecy, while overestimating it may lead to inefficient system design. Therefore, a reliable leakage estimator is essential. Neural network-based estimators provide a data-driven way to estimate…

LLM-based financial agents have attracted widespread excitement for their ability to trade like human experts. However, most systems exhibit a "profit mirage": dazzling back-tested returns evaporate once the model's knowledge window ends,…

The analytic theory presented in Paper I is converted into a form convenient for numerical analysis. A fast and accurate code has been written using this numerical formulation. The results are presented by first defining a reference set of…

Backtesting LLMs on resolved events assumes models reason only from pre-cutoff knowledge, yet pretrained models inevitably leak post-cutoff knowledge. We introduce a claim-level evaluation framework that decomposes prediction rationales…

While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training images and thus leak privacy-sensitive training information. In…

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such…

The problem of determining the intrinsic quality of a signal processing system with respect to the inference of an unknown deterministic parameter $\theta$ is considered. While the Fisher information measure $F(\theta)$ forms a classical…

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.…

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.…