Related papers: Measuring Leakage in Concept-Based Methods: An Inf…

Concept Bottleneck Models (CBMs) map dense feature representations into human-interpretable concepts which are then combined linearly to make a prediction. However, modern CBMs rely on the CLIP model to obtain image-concept annotations, and…

Automated ICD-10 coding from clinical discharge summaries requires models that are both accurate on long-tailed multi-label classification tasks and interpretable to clinicians. Concept Bottleneck Models (CBMs) offer a principled framework…

Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for…

Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowledge can contain private information that may be leaked when…

Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while task-relevant information is maximized. However, a rigorous…

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…

The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs), are not designed to solve relational problems, while…

Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creating tension between…

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model…

Machine learning (ML) models benefit from large datasets. Collecting data in biomedical domains is costly and challenging, hence, combining datasets has become a common practice. However, datasets obtained under different conditions could…

Open-ended grading is central to equitable and personalized education, yet manual grading remains time-consuming and costly, underscoring the need for automated grading systems. Although recent neural and large language model (LLM) based…

This paper introduces a case study that involves data leakage in a bank applying the so-called Thinging Machine (TM) model. The aim is twofold: (1) Presenting a systematic conceptual framework for the leakage problem that provides a…

Simplistic estimation of neural connectivity in MEEG sensor space is impossible due to volume conduction. The only viable alternative is to carry out connectivity estimation in source space. Among the neuroscience community this is claimed…

This paper investigates a multi-terminal source coding problem under a logarithmic loss fidelity which does not necessarily lead to an additive distortion measure. The problem is motivated by an extension of the Information Bottleneck…

Deep learning-based medical image classification techniques are rapidly advancing in medical image analysis, making it crucial to develop accurate and trustworthy models that can be efficiently deployed across diverse clinical scenarios.…

In modern social networks, existing style transfer methods suffer from a serious content leakage issue, which hampers the ability to achieve serial and reversible stylization, thereby hindering the further propagation of stylized images in…

Given two random variables $X$ and $Y$, an operational approach is undertaken to quantify the ``leakage'' of information from $X$ to $Y$. The resulting measure $\mathcal{L}(X \!\! \to \!\! Y)$ is called \emph{maximal leakage}, and is…

Large Language Models (LLMs) store an extensive amount of factual knowledge obtained from vast collections of text. To effectively utilize these models for downstream tasks, it is crucial to have reliable methods for measuring their…