Related papers: Architecture-Aware Explanation Auditing for Indust…
Observational models make tractable the analysis of information flow properties by providing an abstraction of side channels. We introduce a methodology and a tool, Scam-V, to validate observational models for modern computer architectures.…
We present a framework for verifying the deterministic structured computations surrounding a large language model rather than the model itself, extending a Lean 4 trust-boundary architecture to the generic interfaces of modern LLM…
Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have…
Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the…
While the robustness of vision models is often measured, their dependence on specific architectural design choices is rarely dissected. We investigate why certain vision architectures are inherently more robust to additive Gaussian noise…
We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision. NA is a pixel-wise operation, localizing self attention (SA) to the nearest neighboring pixels, and therefore enjoys a…
Image-based quality assessment (QA) in additive manufacturing (AM) often relies heavily on the expertise and constant attention of skilled human operators. While machine learning and deep learning methods have been introduced to assist in…
Nonlinear causal discovery from observational data imposes strict identifiability assumptions on the formulation of structural equations utilized in the data generating process. The evaluation of structure learning methods under assumption…
In sensitive contexts, providers of machine learning algorithms are increasingly required to give explanations for their algorithms' decisions. However, explanation receivers might not trust the provider, who potentially could output…
Securing Internet of Things (IoT) firmware remains difficult due to proprietary binaries, stripped symbols, heterogeneous architectures, and limited access to executable code. Existing analysis methods, such as static analysis, symbolic…
Current evaluation of mathematical reasoning in language models relies primarily on answer accuracy, potentially masking fundamental failures in logical computation. We introduce a diagnostic framework that distinguishes genuine…
Visual inspection is the predominant technique for evaluating the condition of civil infrastructure. The recent advances in unmanned aerial vehicles (UAVs) and artificial intelligence have made the visual inspections faster, safer, and more…
A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the queried region should imply a confident, calibrated answer. We test this…
Self-adaptive systems (SASs) adjust their behavior at runtime in response to internal or external change. The MAPE-K model, which includes Monitors, Analyzers, Planners, Executors, and shared Knowledge, is a reference for structuring…
In this study, we take a departure and explore an explainability-driven strategy to data auditing, where actionable insights into the data at hand are discovered through the eyes of quantitative explainability on the behaviour of a dummy…
Class Activation Mapping (CAM) methods are widely used to generate visual explanations for deep learning classifiers in medical imaging. However, existing evaluation frameworks assess whether explanations are correct, measured by…
Artificial intelligence deployment for automated photovoltaic (PV) monitoring faces interpretability barriers that limit adoption in energy infrastructure applications. While deep learning achieves high accuracy in thermal fault detection,…
Turbofan engine degradation under sustained operational stress necessitates robust prognostic systems capable of accurately estimating the Remaining Useful Life (RUL) of critical components. Existing deep learning approaches frequently fail…
Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains. An established approach to interpretability is generating visual attribution maps that…
Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…