Alessio Botta

Software-Defined Wide Area Networks (SD-WAN) offer enhanced flexibility and resilience over traditional WAN architectures by leveraging the Software-Defined Networking (SDN) paradigm. They enable the simultaneous use of multiple WAN connections, potentially across different technologies or service providers, while supporting bandwidth aggregation and improved fault tolerance. However, these connections are abstracted as overlays, concealing the underlying physical network (underlay) from the control plane. As a result, the controller lacks visibility into whether different overlays share critical resources such as links or routers, which can lead to congestion and degraded performance. In this work, we propose an active monitoring framework that classifies overlays as joint or disjoint by analyzing the correlation of latency time series from probe traffic sent across the available overlays. This classification allows the SD-WAN controller to make underlay-aware decisions by selecting only disjoint overlays for routing, thereby minimizing shared bottlenecks. We implement and evaluate our approach in Mininet using a real-world WAN topology. Results indicate that our method achieves accurate overlay classification, leading to substantial gains in throughput, with noticeable reductions in both jitter and latency.

Prostate cancer is one of the most common malignancies in men. It can be treated with prostatectomy, a surgical procedure that may result in postoperative sexual dysfunction. To effectively counsel patients and to anticipate potential complications, this work adopts traditional statistical methods and machine learning to predict patients’ sexual satisfaction one year post-surgery. A retrospective, single-center cohort study was conducted involving 409 patients, with a median age of 72 years. This cohort was derived from an initial population of 524 individuals, following the exclusion of cases with incomplete EPIC-26 Q12 data at the 12-month follow-up. We studied medical patients from the University Hospital of Naples “Federico II”, focusing on evaluations before and one year after surgery. Patients’ satisfaction with their sexual function was measured using question 12 from the Expanded Prostate Index Composite (EPIC-26). Statistical results showed a positive link between the International Prostate Symptom Score (IPSS) and sexual dissatisfaction after surgery. Pre-operative higher IPSS scores were associated with lower sexual satisfaction. However, most patients did not experience a significant drop in sexual satisfaction one year after surgery. Scores on the International Index of Erectile Function (IIEF) and EPIC-26-Q12 exhibit, in fact, an interesting inverse relationship, indicating that higher pre-operative scores on one correspond to lower scores on the other. Machine learning techniques on the other hand, allow a prediction accuracy of 81% for post-operative sexual impairment, with the Extra-Trees classifier yielding the best performance. The achieved prediction accuracy of 81% suggests that machine learning models may serve as valuable tools for preoperative risk stratification and for providing personalized patient counseling regarding postoperative sexual function. This study shows how the combination of statistical approaches and machine learning can improve sexual health management after prostate radical surgery, providing insights for doctors and patients, while further validation involving larger and multicenter datasets is necessary, these findings underscore the significant clinical potential of incorporating statistical and machine learning methodologies into the management of postoperative sexual health.

The complexity and scale of Internet attacks call for distributed, cooperative observatories capable of monitoring malicious traffic across diverse networks. Holoscope is a lightweight, cloud-native platform designed to simplify the deployment and management of distributed telescope (passive) and honeypot (active) sensors, used to collect and analyse attack traffic by exposing or simulating vulnerable systems. Built upon K3s and WireGuard, Holoscope offers secure connectivity, automated node onboarding, and resilient operation even in resource-constrained environments. Through modular design and Infrastructure-as-Code principles, it supports dynamic sensor orchestration, automated recovery and processing. We build, deploy and operate Holoscope across multiple institutions and cloud networks in Europe and Brazil, enabling unified visibility into large-scale attack phenomena while maintaining ease of integration and security compliance.