Search

Abstract Most of the intrusion detection datasets to research machine learning-based intrusion detection systems (IDSs) are devoted to cyber-only systems, and they typically collect data from one architectural layer. Often the attacks are generated in dedicated attack sessions, without reproducing the realistic alternation and overlap of normal and attack actions. We present a dataset for intrusion detection by performing penetration testing on an embedded cyber-physical system built over Robot Operating System 2 (ROS2). Features are monitored from three architectural layers: the Linux operating system, the network, and the ROS2 services. The dataset is structured as a time series and describes the expected behavior of the system and its response to ROS2-specific attacks: it repeatedly alternates periods of attack-free operation with periods when a specific attack is being performed. This allows measuring the time to detect an attacker and the number of malicious activities performed before detection. Also, it allows training an intrusion detector to minimize both, by taking advantage of the numerous alternating periods of normal and attack operations.

Delirium, a multifactorial condition with an acute onset and diverse clinical manifestations, poses a significant challenge in the care of hospitalized individuals aged 65 years and older. This study aimed to evaluate the level of knowledge among nursing healthcare personnel regarding the diagnosis, recognition of complications, and treatment of delirium. A paper questionnaire consisting of 18 multiple-choice questions was distributed to nurses in twelve operational units located in four facilities within a local hospital in a specific geographical region under the jurisdiction of the Romagna Local Health Authority in Italy. Out of 194 respondents, the overall acceptance rate was 64.2%. The findings revealed an insufficient understanding of delirium among the nursing staff, with more than 40% of respondents answering incorrectly to five out of nine questions related to delirium knowledge, diagnosis, prevention, and treatment. Notably, gender emerged as a significant determinant, with female participants exhibiting a substantial odds ratio (OR) of 3.50 (p = 0.011 and CI95% = 1.34–9.16) compared to their male counterparts, indicating a higher likelihood of receiving delirium training among females. Furthermore, prolonged tenure within the same work context was associated with a reduced likelihood of receiving delirium training compared to those with less than two years of experience (OR = 0.21, p = 0.034, and CI95% = 0.05–0.89 for 6–10 years of tenure; OR = 0.22, p = 0.038, and CI95% = 0.05–0.92 for over 10 years of tenure). This study underscores the urgent need for enhanced delirium education and improved strategies among nurses to effectively manage patients with delirium. The results advocate regular educational sessions utilizing diverse formats to comprehensively address knowledge gaps among nursing staff. This study was not registered.

In Italy, free vaccinations for Herpes Zoster (HZ), pneumococcal (PCV), and influenza (FLU) are recommended each year for individuals turning 65. Despite this, achieving optimal vaccination coverage remains challenging. This study assesses coverage rates for HZ, PCV, and FLU in Forlì, Northern Italy, and examines how altitude, urban planning, and health organization variables (such as the presence of a vaccination center) impact vaccine uptake. Vaccination coverages were calculated for birth cohorts between 1952 and 1958 for each municipality in the Forlì area as of 1 March 2024. The geographical factors influencing the vaccination uptake were extracted from the Italian National Institute of Statistics (ISTAT) records and evaluated through a multivariate analysis. The sample analyzed included 15,272 vaccine campaign targets from Forlì’s province (185,525 citizens); the vaccine uptake rates for HZ, PCV, and FLU were 26.9%, 36.7%, and 43.5%, respectively. Gender did not appear to influence vaccine uptake. Living in a flat area appeared to increase vaccine uptake in a statistically significant way for all the vaccinations when compared to a mountainous area (HZ: OR: 1.50, PCV: OR: 1.33, FLU: OR: 1.67). The presence of a vaccine service in low-urbanized areas was shown to increase vaccine uptake for all vaccinations (HZ: OR: 1.65, PCV: OR: 1.93, FLU: OR: 1.53) compared with low-urbanized areas without a vaccination center or more urbanized areas with a vaccination center. This study emphasizes the significance of the territorial context, along with the ease of access to vaccinations and geographic barriers, as key determinants in achieving vaccination targets. Local health authorities should consider these factors when implementing vaccination campaigns.

We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Especially, this applies to objects that can impact the actor’s safety and reliability. To quantify the impact of object (mis)detection on safety and reliability in the context of autonomous driving, we propose new object detection measures that reward the correct identification of objects that are most dangerous and most likely to affect driving decisions. To achieve this, we build an object criticality model to reward the detection of the objects based on proximity, orientation, and relative velocity with respect to the subject vehicle. Then, we apply our model on the recent autonomous driving dataset nuScenes, and we compare nine object detectors. Results show that, in several settings, object detectors that perform best according to the nuScenes ranking are not the preferable ones when the focus is shifted on safety and reliability.

Deep Neural Networks (DNNs) have become an enabling technology for building accurate image classifiers, and are increasingly being applied in many ICT systems such as autonomous vehicles. Unfortunately, classifiers can be deceived by images that are altered due to failures of the visual camera, preventing the proper execution of the classification process. Therefore, it is of utmost importance to build image classifiers that can guarantee accurate classification even in the presence of such camera failures. This study crafts classifiers that are robust to failures of the visual camera by augmenting the training set with artificially altered images that simulate the effects of such failures. Such a data augmentation approach improves classification accuracy with respect to the most common data augmentation approaches, even in the absence of camera failures. To provide experimental evidence for our claims, we exercise three DNN image classifiers on three image datasets, in which we inject the effects of many failures into the visual camera. Finally, we applied eXplainable AI to debate why classifiers trained with the data augmentation approach proposed in this study can tolerate failures of the visual camera.

The Herpes Zoster (HZ) vaccination has proven both safe and effective in alleviating conditions related to HZ, leading to significant cost savings in national healthcare and social systems. In Italy, it is recommended and provided free of charge to individuals aged 65 and older. To achieve broad vaccination coverage, alongside ordinary immunization campaigns, active and catch-up campaigns were implemented. This retrospective observational study aimed to observe the vaccination coverage achieved in the Romagna Local Health Authority (LHA) during the 2023 active campaign, with a secondary goal of assessing the impact of the 2022 catch-up campaign and the 2023 active campaign compared to ordinary campaigns. As of 3 July 2023, an overall vaccine uptake of 13.5% was achieved among individuals born in 1958, with variations among the four LHA centers ranging from 10.2% to 17.7%. Catch-up and active campaigns together contributed to nearly half of the achieved coverage in Center No. 1 and a quarter in Center No. 2. Notably, individuals born in 1957, not included in the Center No. 2 catch-up campaign, reached significantly lower vaccination coverage compared to other cohorts and centers. Analyzing the use of text messages for active campaigns, it was observed that cohort groups did not show substantial differences in text-message utilization for warnings. However, having relatives who had experienced HZ-related symptoms significantly reduced the reliance on text messages as warnings. These results highlighted how catch-up and active campaigns effectively increased vaccine coverage. Nevertheless, differences in uptake among different centers within the same LHA and the limited contribution of other information sources compared to text messages suggest the necessity of designing campaigns involving all available channels and stakeholders to maximize vaccine uptake.

Failures of the vehicle camera may compromise the correct acquisition of frames, that are subsequently used by autonomous driving tasks. A clear understanding of the behavior of the autonomous driving tasks under such failure conditions, together with strategies to avoid safety is jeopardized, are indeed necessary. This study analyses and improve the performance of Traffic Sign Recognition (TSR) systems for road vehicles under the possible occurrence of camera failures. Our experimental assessment relies on three public datasets, which are commonly used for benchmarking TSR systems. We artificially inject 13 different types of camera failures into the three datasets. Then, we exploit three deep neural networks (DNNs) to classify either a single frame of a traffic sign or a sequence (i.e., a sliding window) of frames. We show that sliding windows significantly improves the robustness of the classifier against altered frames. We confirm our observations through explainable AI, which allows understanding why different classifiers have different performance in case of camera failures.

Community-oriented primary care (COPC) is an inclusive healthcare approach that combines individual care with a population-based outlook, striving to offer effective and equitable services. This study concentrates on assessing the perceived quality of a “Casa della Comunità” (CdC) implemented by the Romagna Local Health Authority, which embraces the COPC model. Through the examination of user experiences, the study aims to comprehend the influence of the CdC’s care delivery model on the community’s perception of service quality. From 13–18 March 2023, paper questionnaires were distributed by trained healthcare professionals and volunteers. The cross-sectional study enrolled participants aged 18 or older, capable of understanding written Italian, and willing to take part voluntarily. A total of 741 questionnaires were collected, resulting in an overall acceptance rate of 85.6%. Among the respondents, 37.9% were female, with an average age of 55.4 ± 16.2 years. While the respondents generally held a positive view of the quality, the results displayed varying levels of satisfaction across the different areas. Multivariate analysis revealed significant associations between factors such as gender, employment status, financial resources, education level, and distance from the healthcare center with the perceived quality of the facility in terms of accessibility, environment, staff, continuity of care, and overall satisfaction. The study yielded valuable insights, identifying strengths and areas for improvement and underscoring the importance of ongoing monitoring studies to enhance patient satisfaction continuously.

Abstract Railway systems are composed of a multitude of subsystems, sensors, and actuators that exchange datagrams through safety-critical communication protocols. However, the vast majority of these protocols rely on ad hoc interlacing mechanisms and safety codes which raise the heterogeneity and complexity of the overarching railway system. Therefore, Rete Ferroviaria Italiana, the company who is in charge of managing the Italian railway network, coordinated the definition of the Protocollo Vitale Standard (Standard Vital Protocol). This protocol is inspired to, and compliant with, the communication protocols adopted for the European Train Control System (ETCS) (SUBSET, UNISIG, 037, Euroradio FIS, version 2.3. 0; SUBSET, UNISIG, 098, RBC-RBC safe communication interface, 2007), and it is meant to become the standard layer to enable safe communication between components of the Italian railway system. This paper reports our experience in the design, implementation, verification, and validation of the Protocollo Vitale Standard in compliance with the European safety standards for railway systems. We first defined a safety plan and a verification and validation plan, which guide the design, development, verification, and validation activities as required by safety standards. Guidelines of such plans have been followed strictly until completion of the work, which concludes with the provision of a safety case where all safety evidences are summarized. Noticeably, we (i) selected appropriate safety mechanisms, (ii) verified the software design, (iii) implemented the software in compliance with code metrics and coding rules, (iv) conducted tests to validate the protocol against its functional and performance requirements, and ultimately (v) devised all relevant documentation and a safety case which summarizes the evidences needed for certification.

In the last decade, researchers, practitioners and companies struggled for devising mechanisms to detect cyber-security threats. Among others, those efforts originated rule-based, signature-based or supervised Machine Learning (ML) algorithms that were proven effective for detecting those intrusions that have already been encountered and characterized. Instead, new unknown threats, often referred to as zero-day attacks or zero-days, likely go undetected as they are often misclassified by those techniques. In recent years, unsupervised anomaly detection algorithms showed potential to detect zero-days. However, dedicated support for quantitative analyses of unsupervised anomaly detection algorithms is still scarce and often does not promote meta-learning, which has potential to improve classification performance. To such extent, this paper introduces the problem of zero-days and reviews unsupervised algorithms for their detection. Then, the paper applies a question-answer approach to identify typical issues in conducting quantitative analyses for zero-days detection, and shows how to setup and exercise unsupervised algorithms with appropriate tooling. Using a very recent attack dataset, we debate on i) the impact of features on the detection performance of unsupervised algorithms, ii) the relevant metrics to evaluate intrusion detectors, iii) means to compare multiple unsupervised algorithms, iv) the application of meta-learning to reduce misclassifications. Ultimately, v) we measure detection performance of unsupervised anomaly detection algorithms with respect to zero-days. Overall, the paper exemplifies how to practically orchestrate and apply an appropriate methodology, process and tool, providing even non-experts with means to select appropriate strategies to deal with zero-days.

Deep Neural Networks (DNNs) are the preferred choice for image-based machine learning applications in several domains. However, DNNs are vulnerable to adversarial attacks, that are carefully-crafted perturbations introduced on input images to fool a DNN model. Adversarial attacks may prevent the application of DNNs in security-critical tasks: consequently, relevant research effort is put in securing DNNs. Typical approaches either increase model robustness, or add detection capabilities in the model, or operate on the input data. Instead, in this paper we propose to detect ongoing attacks through monitoring performance indicators of the underlying Graphics Processing Unit (GPU). In fact, adversarial attacks generate images that activate neurons of DNNs in a different way than legitimate images. This also causes an alteration of GPU activities, that can be observed through software monitors and anomaly detectors. This paper presents our monitoring and detection system, and an extensive experimental analysis that includes a total of 14 adversarial attacks, 3 datasets, and 12 models. Results show that, despite limitations on the monitoring resolution, adversarial attacks can be detected in most cases, with peaks of detection accuracy above 90%.

Herpes Zoster (shingles) is an infection that occurs when varicella-zoster virus reactivates from the latent state. Incidence and severity of Herpes Zoster disease increase with age. Antiviral drugs are the elective treatment; however, prevention of disease reactivation through effective and safe vaccines is available in Italy out-of-pocket from age 65 onwards. The Romagna Local Health Authority (northern Italy) administered catch-up vaccinations in March–May 2022 for immunizations not performed during the COVID-19 pandemic. In this study, adherence rates to the catch-up campaign and recall activities adopted in two centers were investigated. The uptakes for only the catch-up vaccinations were 11.4% and 12.4%. Having suffered from Herpes Zoster or having family members who suffered from it would not seem to be drivers of increased uptake. Although sending text-messages to all involved patients was the main motivation for vaccine uptake (85.7–95.1%), word of mouth and web/news advertising also contributed to adoption in Center No. 2. In both centers, the need for greater synergy between public health departments and general practitioners to engage their patients emerged, as did the need for additional recall measures. Studying the main drivers of vaccine hesitancy, especially at the local level, can help in targeting campaigns and catch-up activities in order to achieve widespread acceptance.