相关论文: Learning Contextual Runtime Monitors for Safe AI-B…

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

We introduce a unified Learning Context (LC) framework designed to transition AI-based education from context-blind mimicry to a principled, holistic understanding of the learner. This white paper provides a multidisciplinary roadmap for…

Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context to identify and mitigate potential risks. Though researchers…

For machine learning components used as part of autonomous systems (AS) in carrying out critical tasks it is crucial that assurance of the models can be maintained in the face of post-deployment changes (such as changes in the operating…

Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML predictions are used in safety-critical applications, like…

Medical Cyber-physical Systems (MCPS) are vulnerable to accidental or malicious faults that can target their controllers and cause safety hazards and harm to patients. This paper proposes a combined model and data-driven approach for…

Learning-based model predictive control has been widely applied in autonomous racing to improve the closed-loop behaviour of vehicles in a data-driven manner. When environmental conditions change, e.g., due to rain, often only the…

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

Safety filters in control systems correct nominal controls that violate safety constraints. Designing such filters as functions of visual observations in uncertain and complex environments is challenging. Several deep learning-based…

Recent advances in learning techniques have garnered attention for their applicability to a diverse range of real-world sequential decision-making problems. Yet, many practical applications have critical constraints for operation in real…

With the increasing use of Machine Learning (ML) in critical autonomous systems, runtime monitors have been developed to detect prediction errors and keep the system in a safe state during operations. Monitors have been proposed for…

High-accurate machine learning (ML) image classifiers cannot guarantee that they will not fail at operation. Thus, their deployment in safety-critical applications such as autonomous vehicles is still an open issue. The use of fault…

Monitoring AIs at runtime can help us detect and stop harmful actions. In this paper, we study how to efficiently combine multiple runtime monitors into a single monitoring protocol. The protocol's objective is to maximize the probability…

Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety…

Context: Dynamic production environments make it challenging to maintain reliable machine learning (ML) systems. Runtime issues, such as changes in data patterns or operating contexts, that degrade model performance are a common occurrence…

Given the inherent non-deterministic nature of machine learning (ML) systems, their behavior in production environments can lead to unforeseen and potentially dangerous outcomes. For a timely detection of unwanted behavior and to prevent…

Student mental health is an increasing concern in academic institutions, where stress can severely impact well-being and academic performance. Traditional assessment methods rely on subjective surveys and periodic evaluations, offering…

We examine Contextualized Machine Learning (ML), a paradigm for learning heterogeneous and context-dependent effects. Contextualized ML estimates heterogeneous functions by applying deep learning to the meta-relationship between contextual…

The performance of machine learning model can be further improved if contextual cues are provided as input along with base features that are directly related to an inference task. In offline learning, one can inspect historical training…

Model Predictive Control (MPC) is a powerful control strategy widely utilized in domains like energy management, building control, and autonomous systems. However, its effectiveness in real-world settings is challenged by the need to…