Related papers: Tree-Based Leakage Inspection and Control in Conce…

Side-channel attacks that leak sensitive information through a computing device's interaction with its physical environment have proven to be a severe threat to devices' security, particularly when adversaries have unfettered physical…

Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these *unverbalized biases*. Monitoring models via their stated reasoning is therefore…

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…

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…

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…

In recent years, Visual Anomaly Detection (VAD) has gained significant attention due to its ability to identify defects using only normal images during training. Many VAD models work without supervision but are still able to provide visual…

Successful group meetings, such as those implemented in group behavioral-change programs, work meetings, and other social contexts, must promote individual goal setting and execution while strengthening the social relationships within the…

Large language models (LLMs) have advanced natural language processing (NLP) skills such as through next-token prediction and self-attention, but their ability to integrate broad context also makes them prone to incorporating irrelevant…

Deep learning has achieved remarkable success in image recognition, yet their inherent opacity poses challenges for deployment in critical domains. Concept-based interpretations aim to address this by explaining model reasoning through…

Leak detection in gas pipelines is an important and persistent problem in the Oil and Gas industry. This is particularly important as pipelines are the most common way of transporting natural gas. This research aims to study the ability of…

Voice disorders affect a significant portion of the population, and the ability to diagnose them using automated, non-invasive techniques would represent a substantial advancement in healthcare, improving the quality of life of patients.…

With growing demand for interpretability in deep learning, especially in high stakes domains, Concept Bottleneck Models (CBMs) address this by inserting human understandable concepts into the prediction pipeline, but they are generally…

Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown that LLMs' latent…

Accurate streamflow prediction largely relies on historical meteorological records and streamflow measurements. For many regions, however, such data are only scarcely available. Facing this problem, many studies simply trained their machine…

Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the…

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Learned Cost Models (LCMs) have shown superior results over traditional database cost models as they can significantly improve the accuracy of cost predictions. However, LCMs still fail for some query plans, as prediction errors can be…

Machine learning (ML) approaches to data analysis are now widely adopted in many fields including epidemiology and medicine. To apply these approaches, confounds must first be removed as is commonly done by featurewise removal of their…

To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable…