相关论文: Towards a Computational Analysis of Suspense: Dete…

This paper addresses the issue of defining context, and more specifically the different contexts needed for understanding a particular type of texts. The corpus chosen is homogeneous and allows us to determine characteristic properties of…

As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…

Software development is a complex activity which depends on diverse technologies and people's expertise. The approaches to developing software highly depend on these different characteristics, which are the context developers are subject…

From the climate system to the effect of the internet on society, chaotic systems appear to have a significant role in our future. Here a method of statistical learning for a class of chaotic systems is described along with underlying…

Informational bias is widely present in news articles. It refers to providing one-sided, selective or suggestive information of specific aspects of certain entity to guide a specific interpretation, thereby biasing the reader's opinion.…

The online spreading of fake news is a major issue threatening entire societies. Much of this spreading is enabled by new media formats, namely social networks and online media sites. Researchers and practitioners have been trying to answer…

This research recasts ransomware detection using performance monitoring and statistical machine learning. The work builds a test environment with 41 input variables to label and compares three computing states: idle, encryption and…

The task of text and sentence classification is associated with the need for large amounts of labelled training data. The acquisition of high volumes of labelled datasets can be expensive or unfeasible, especially for highly-specialised…

The field of information retrieval often works with limited and noisy data in an attempt to classify documents into subjective categories, e.g., relevance, sentiment and controversy. We typically quantify a notion of agreement to understand…

Over the last years, we have seen several security incidents that compromised system safety, of which some caused physical harm to people. Meanwhile, various risk assessment methods have been developed that integrate safety and security,…

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

Any autonomous controller will be unsafe in some situations. The ability to quantitatively identify when these unsafe situations are about to occur is crucial for drawing timely human oversight in, e.g., freight transportation applications.…

This paper introduces the Grievance Dictionary, a psycholinguistic dictionary which can be used to automatically understand language use in the context of grievance-fuelled violence threat assessment. We describe the development the…

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

As language models evolve into autonomous agents that act and communicate on behalf of users, ensuring safety in multi-agent ecosystems becomes a central challenge. Interactions between personal assistants and external service providers…

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…

Insider threats is the most concerned cybersecurity problem which is poorly addressed by widely used security solutions. Despite the fact that there have been several scientific publications in this area, but from our innovative study…

Monitoring is an important aspect of safely deploying Large Language Models (LLMs). This paper examines activation probes for detecting ``high-stakes'' interactions -- where the text indicates that the interaction might lead to significant…

Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes…

Extracting interesting scenarios from real-world data as well as generating failure cases is important for the development and testing of autonomous systems. We propose efficient mechanisms to both characterize and generate testing…