Related papers: Learning Password Best Practices Through In-Task I…

When using security questions most users still trade-off security for the convenience of memorability. This happens because most users find strong answers to security questions difficult to remember. Previous research in security education…

Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables…

Privacy policies are intended to support informed consent, yet users rarely read them fully. This study examines how common privacy policy interface structures influence attention allocation, reading behavior, and perceived experience.…

Puzzle-based training is a common type of hands-on activity accompanying formal and informal cybersecurity education, much like programming or other IT skills. However, there is a lack of tools to help the educators with the post-training…

Design features of social media platforms, such as infinite scroll, increase users' likelihood of experiencing normative dissociation -- a mental state of absorption that diminishes self-awareness and disrupts memory. This paper…

While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems. Yet, frictionless dialogue risks fostering uncritical…

Prior work has shown that safety interventions applied during pretraining, such as removing and rephrasing harmful content, can substantially improve the robustness of the resulting models. In this paper, we study the fundamental question…

Researchers have extensively explored how password creation policies influence the security and usability of user-chosen passwords, producing evidence-based policy guidelines. However, for web authentication to improve in practice, websites…

During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundings. Often, dangerous…

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…

As robots increasingly operate in shared, safety critical environments, acting safely is no longer sufficient robots must also make their safety decisions intelligible to human collaborators. In human robot collaboration (HRC), behaviours…

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding…

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time,…

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a…

Recent advances in Deep Machine Learning have shown promise in solving complex perception and control loops via methods such as reinforcement and imitation learning. However, guaranteeing safety for such learned deep policies has been a…

Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23…

Collaborative learning is an educational approach that enhances learning through shared goals and working together. Interaction and regulation are two essential factors related to the success of collaborative learning. Since the information…

In this paper, we study the learning of safe policies in the setting of reinforcement learning problems. This is, we aim to control a Markov Decision Process (MDP) of which we do not know the transition probabilities, but we have access to…