Related papers: Quantifying Robustness: A Benchmarking Framework f…

Increasingly deeper integration of HPC resources and QPUs unveils new challenges in computer architecture and engineering. As a consequence, dependability arises again as a concern encompassing resilience, reproducibility and security. The…

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Cyber-physical systems (CPS) incorporate the complex and large-scale engineered systems behind critical infrastructure operations, such as water distribution networks, energy delivery systems, healthcare services, manufacturing systems, and…

Robustness is a crucial factor for the successful deployment of robots in unstructured environments, particularly in the domain of Simultaneous Localization and Mapping (SLAM). Simulation-based benchmarks have emerged as a highly scalable…

Despite achieving excellent performance on benchmarks, deep neural networks often underperform in real-world deployment due to sensitivity to minor, often imperceptible shifts in input data, known as distributional shifts. These shifts are…

Energy-based learning algorithms, such as predictive coding (PC), have garnered significant attention in the machine learning community due to their theoretical properties, such as local operations and biologically plausible mechanisms for…

Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states…

The design and deployment of autonomous systems for space missions require robust solutions to navigate strict reliability constraints, extended operational duration, and communication challenges. This study evaluates the stability and…

Traditional Cyber-physical Systems(CPSs) were not built with cybersecurity in mind. They operated on separate Operational Technology (OT) networks. As these systems now become more integrated with Information Technology (IT) networks based…

Due to the diffusion of IoT, modern software systems are often thought to control and coordinate smart devices in order to manage assets and resources, and to guarantee efficient behaviours. For this class of systems, which interact…

Non-adversarial robustness, also known as natural robustness, is a property of deep learning models that enables them to maintain performance even when faced with distribution shifts caused by natural variations in data. However, achieving…

Studying the robustness of machine learning models is important to ensure consistent model behaviour across real-world settings. To this end, adversarial robustness is a standard framework, which views robustness of predictions through a…

Aiming at analyzing performance in cloud computing, some unpredictable perturbations which may lead to performance downgrade are essential factors that should not be neglected. To avoid performance downgrade in cloud computing system, it is…

This research leverages Conformal Prediction (CP) in the form of Conformal Predictive Systems (CPS) to accurately estimate uncertainty in a suite of machine learning (ML)-based radio metric models [1] as well as in a 2-D map-based ML path…

The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time control deadlines.…

The integration of machine learning (ML) into cyber-physical systems (CPS) offers significant benefits, including enhanced efficiency, predictive capabilities, real-time responsiveness, and the enabling of autonomous operations. This…

This paper introduces a notation of $\varepsilon$-weakened robustness for analyzing the reliability and stability of deep neural networks (DNNs). Unlike the conventional robustness, which focuses on the "perfect" safe region in the absence…

Deep learning models for medical image segmentation and object detection are becoming increasingly available as clinical products. However, as details are rarely provided about the training data, models may unexpectedly fail when cases…

Deep learning models are notoriously vulnerable to imperceptible perturbations. Most existing research centers on adversarial robustness (AR), which evaluates models under worst-case scenarios by examining the existence of deterministic…

Resource theories provide a general framework for the characterization of properties of physical systems in quantum mechanics and beyond. Here, we introduce methods for the quantification of resources in general probabilistic theories…