Related papers: SPLAIN: Augmenting Cybersecurity Warnings with Rea…
Explanation generation frameworks aim to make AI systems' decisions transparent and understandable to human users. However, generating explanations in uncertain environments characterized by incomplete information and probabilistic models…
Plain Language Summaries (PLS) aim to make research accessible to lay readers, but they are typically written in a one-size-fits-all style that ignores differences in readers' information needs and comprehension. In health contexts, this…
Neural networks lack the ability to reason about qualitative physics and so cannot generalize to scenarios and tasks unseen during training. We propose ESPRIT, a framework for commonsense reasoning about qualitative physics in natural…
We introduce Explearn, an online algorithm that learns to jointly output predictions and explanations for those predictions. Explearn leverages Gaussian Processes (GP)-based contextual bandits. This brings two key benefits. First, GPs…
Natural language explanations have the potential to provide rich information that in principle guides model reasoning. Yet, recent work by Lampinen et al. (2022) has shown limited utility of natural language explanations in improving…
Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such…
Cyber Threat Intelligence (CTI) reporting is pivotal in contemporary risk management strategies. As the volume of CTI reports continues to surge, the demand for automated tools to streamline report generation becomes increasingly apparent.…
Unlike the flow structure of natural languages, programming languages have an inherent rigidity in structure and grammar.However, existing detection methods based on pre-trained models typically treat code as a natural language sequence,…
Understanding a Reinforcement Learning (RL) policy is crucial for ensuring that autonomous agents behave according to human expectations. This goal can be achieved using Explainable Reinforcement Learning (XRL) techniques. Although textual…
Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…
Cyberbullying has become a big issue with the popularity of different social media networks and online communication apps. While plenty of research is going on to develop better models for cyberbullying detection in monolingual language,…
We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable constraints within flexible neural function…
Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by…
Satellite networks are vital in facilitating communication services for various critical infrastructures. These networks can seamlessly integrate with a diverse array of systems. However, some of these systems are vulnerable due to the…
Computer Emergency Response Teams (CERTs) face increasing challenges processing the growing volume of security-related information. Daily manual analysis of threat reports, security advisories, and vulnerability announcements leads to…
The rapid advancement of artificial intelligence (AI) has significantly expanded the attack surface for AI-driven cybersecurity threats, necessitating adaptive defense strategies. This paper introduces CyberSentinel, a unified, single-agent…
Traffic analysis attacks pose a major risk for online security. Distinctive patterns in communication act as fingerprints, enabling adversaries to de-anonymise communicating parties or to infer sensitive information. Despite the attacks…
Recent studies have exploited advanced generative language models to generate Natural Language Explanations (NLE) for why a certain text could be hateful. We propose the Chain of Explanation (CoE) Prompting method, using the heuristic words…
Formal control of cyber-physical systems allows for synthesis of control strategies from rich specifications such as temporal logics. However, the classes of systems that the formal approaches can be applied to is limited due to the…
In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain. The pipeline…