相关论文: Verification of Hierarchical Artifact Systems
Deductive verification is an effective method to ensure that a given system exposes the intended behavior. In spite of its proven usefulness and feasibility in selected projects, deductive verification is still not a mainstream technique.…
In representation learning, there has been recent interest in developing algorithms to disentangle the ground-truth generative factors behind a dataset, and metrics to quantify how fully this occurs. However, these algorithms and metrics…
In many real-world scenarios, such as gas leak detection or environmental pollutant tracking, solving the Inverse Source Localization and Characterization problem involves navigating complex, dynamic fields with sparse and noisy…
Contemporary approaches to assisted scientific discovery use language models to automatically generate large numbers of potential hypothesis to test, while also automatically generating code-based experiments to test those hypotheses. While…
The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. In traditional system development,…
AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of \emph{epistemic pollution} in our scientific systems, where unreliable but plausible-looking artifacts can…
For many practical problems, the regression models follow the strong heredity property (also known as the marginality), which means they include parent main effects when a second-order effect is present. Existing methods rely mostly on…
As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are…
Large language models (LLMs) have achieved remarkable success across diverse natural language processing tasks but face persistent challenges in inference efficiency due to their autoregressive nature. While speculative decoding and beam…
Modern AI systems are man-made objects that leverage machine learning to support our lives across a myriad of contexts and applications. Despite extensive epistemological and ethical debates, their metaphysical foundations remain relatively…
Inaccuracies in conventional dependency-tracking methods frequently undermine the security and integrity of modern software supply chains. This paper introduces a kernel-level framework leveraging extended Berkeley Packet Filter (eBPF) to…
We present a security framework that strengthens distributed machine learning by standardizing integrity protections across CPU and GPU platforms and significantly reducing verification overheads. Our approach co-locates integrity…
Mechanical and thermodynamic properties, including the influence of crystal defects, are critical for evaluating materials in engineering applications. Molecular dynamics simulations provide valuable insight into these mechanisms at the…
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…
Many software engineering studies or tasks rely on categorizing software engineering artifacts. In practice, this is done either by defining simple but often imprecise heuristics, or by manual labelling of the artifacts. Unfortunately,…
Hierarchical inference in (generalized) regression problems is powerful for finding significant groups or even single covariates, especially in high-dimensional settings where identifiability of the entire regression parameter vector may be…
Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii)…
Data-centric dynamic systems are systems where both the process controlling the dynamics and the manipulation of data are equally central. In this paper we study verification of (first-order) mu-calculus variants over relational…
Research software is an integral part of most research today and it is widely accepted that research software artifacts should be accessible and reproducible. However, the sustainable archival of research software artifacts is an ongoing…
Gradient boosted models are a fundamental machine learning technique. Robustness to small perturbations of the input is an important quality measure for machine learning models, but the literature lacks a method to prove the robustness of…