Data breach - services for threat detection, analysis and response

Nel mondo della sicurezza informatica, le tecnologie si evolvono per far fronte alle minacce. Non è possibile prescindere dalla prevenzione, ma occorre accettare il fatto che nessuna barriera risulterà impenetrabile e che la rilevazione, unitamente ad una pronta risposta, rappresenta una linea estremamente critica di difesa, ma l’unica veramente attuabile per poter guadagnare più tempo possibile o per limitare i danni. Introdurremo quindi un nuovo modello operativo composto da procedure capaci di affrontare le nuove sfide che il malware costantemente offre e allo stesso tempo di sollevare i comparti IT da attività onerose e sempre più complesse, ottimizzandone il processo di comunicazione e di risposta.

Production Lot Detection through Synthetic Generated Data

Correctness of information gathered in production environments is an essential part of quality assurance processes in many industries, this task is often performed by human resources who visually take annotations in various steps of the production flow. Depending on the performed task the correlation between where exactly the information is gathered and what it represents is more than often lost in the process. The lack of labeled data places a great boundary on the application of deep neural networks aimed at object detection tasks, moreover supervised training of deep models requires a great amount of data to be available. Reaching an adequate large collection of labeled images through classic techniques of data annotations is an exhausting and costly task to perform, not always suitable for every scenario. A possible solution is to generate synthetic data that replicates the real one and use it to fine-tune a deep neural network trained on one or more source domains to a different target domain. The purpose of this thesis is to show a real case scenario where the provided data were both in great scarcity and missing the required annotations. Sequentially a possible approach is presented where synthetic data has been generated to address those issues while standing as a training base of deep neural networks for object detection, capable of working on images taken in production-like environments. Lastly, it compares performance on different types of synthetic data and convolutional neural networks used as backbones for the model.

Data-driven Signal Processing per Jamming Detection in Sistemi Satellitari

In questo elaborato vengono analizzate differenti tecniche per la detection di jammer attivi e costanti in una comunicazione satellitare in uplink. Osservando un numero limitato di campioni ricevuti si vuole identificare la presenza di un jammer. A tal fine sono stati implementati i seguenti classificatori binari: support vector machine (SVM), multilayer perceptron (MLP), spectrum guarding e autoencoder. Questi algoritmi di apprendimento automatico dipendono dalle features che ricevono in ingresso, per questo motivo è stata posta particolare attenzione alla loro scelta. A tal fine, sono state confrontate le accuratezze ottenute dai detector addestrati utilizzando differenti tipologie di informazione come: i segnali grezzi nel tempo, le statistical features, le trasformate wavelet e lo spettro ciclico. I pattern prodotti dall’estrazione di queste features dai segnali satellitari possono avere dimensioni elevate, quindi, prima della detection, vengono utilizzati i seguenti algoritmi per la riduzione della dimensionalità: principal component analysis (PCA) e linear discriminant analysis (LDA). Lo scopo di tale processo non è quello di eliminare le features meno rilevanti, ma combinarle in modo da preservare al massimo l’informazione, evitando problemi di overfitting e underfitting. Le simulazioni numeriche effettuate hanno evidenziato come lo spettro ciclico sia in grado di fornire le features migliori per la detection producendo però pattern di dimensioni elevate, per questo motivo è stato necessario l’utilizzo di algoritmi di riduzione della dimensionalità. In particolare, l'algoritmo PCA è stato in grado di estrarre delle informazioni migliori rispetto a LDA, le cui accuratezze risentivano troppo del tipo di jammer utilizzato nella fase di addestramento. Infine, l’algoritmo che ha fornito le prestazioni migliori è stato il Multilayer Perceptron che ha richiesto tempi di addestramento contenuti e dei valori di accuratezza elevati.

Query Library Development and Anomaly Detection on Flight Data

During the last semester of the Master’s Degree in Artificial Intelligence, I carried out my internship working for TXT e-Solution on the ADMITTED project. This paper describes the work done in those months. The thesis will be divided into two parts representing the two different tasks I was assigned during the course of my experience. The First part will be about the introduction of the project and the work done on the admittedly library, maintaining the code base and writing the test suits. The work carried out is more connected to the Software engineer role, developing features, fixing bugs and testing. The second part will describe the experiments done on the Anomaly detection task using a Deep Learning technique called Autoencoder, this task is on the other hand more connected to the data science role. The two tasks were not done simultaneously but were dealt with one after the other, which is why I preferred to divide them into two separate parts of this paper.

Multiple pathogen detection using nanoplasmonic sensing

Opportunistic diseases caused by Human Immunodeficiency Virus (HIV) and Hepatitis B Virus (HBV) is an omnipresent global challenge. In order to manage these epidemics, we need to have low cost and easily deployable platforms at the point-of-care in high congestions regions like airports and public transit systems. In this dissertation we present our findings in using Localized Surface Plasmon Resonance (LSPR)-based detection of pathogens and other clinically relevant applications using microfluidic platforms at the point-of-care setting in resource constrained environment. The work presented here adopts the novel technique of LSPR to multiplex a lab-on-a-chip device capable of quantitatively detecting various types of intact viruses and its various subtypes, based on the principle of a change in wavelength occurring when metal nano-particle surface is modified with a specific surface chemistry allowing the binding of a desired pathogen to a specific antibody. We demonstrate the ability to detect and quantify subtype A, B, C, D, E, G and panel HIV with a specificity of down to 100 copies/mL using both whole blood sample and HIV-patient blood sample discarded from clinics. These results were compared against the gold standard Reverse Transcriptase Polymerase Chain Reaction (RT-qPCR). This microfluidic device has a total evaluation time for the assays of about 70 minutes, where 60 minutes is needed for the capture and 10 minutes for data acquisition and processing. This LOC platform eliminates the need for any sample preparation before processing. This platform is highly multiplexable as the same surface chemistry can be adapted to capture and detect several other pathogens like dengue virus, E. coli, M. Tuberculosis, etc.

An inter-comparison between a VIS/IR and a MW satellite-based methods for cloud detection and classification

This thesis is aimed to assess similarities and mismatches between the outputs from two independent methods for the cloud cover quantification and classification based on quite different physical basis. One of them is the SAFNWC software package designed to process radiance data acquired by the SEVIRI sensor in the VIS/IR. The other is the MWCC algorithm, which uses the brightness temperatures acquired by the AMSU-B and MHS sensors in their channels centered in the MW water vapour absorption band. At a first stage their cloud detection capability has been tested, by comparing the Cloud Masks they produced. These showed a good agreement between two methods, although some critical situations stand out. The MWCC, in effect, fails to reveal clouds which according to SAFNWC are fractional, cirrus, very low and high opaque clouds. In the second stage of the inter-comparison the pixels classified as cloudy according to both softwares have been. The overall observed tendency of the MWCC method, is an overestimation of the lower cloud classes. Viceversa, the more the cloud top height grows up, the more the MWCC not reveal a certain cloud portion, rather detected by means of the SAFNWC tool. This is what also emerges from a series of tests carried out by using the cloud top height information in order to evaluate the height ranges in which each MWCC category is defined. Therefore, although the involved methods intend to provide the same kind of information, in reality they return quite different details on the same atmospheric column. The SAFNWC retrieval being very sensitive to the top temperature of a cloud, brings the actual level reached by this. The MWCC, by exploiting the capability of the microwaves, is able to give an information about the levels that are located more deeply within the atmospheric column.

UWB radar sensor networks: Detection algorithms design and experimental analysis

In the last years radar sensor networks for localization and tracking in indoor environment have generated more and more interest, especially for anti-intrusion security systems. These networks often use Ultra Wide Band (UWB) technology, which consists in sending very short (few nanoseconds) impulse signals. This approach guarantees high resolution and accuracy and also other advantages such as low price, low power consumption and narrow-band interference (jamming) robustness. In this thesis the overall data processing (done in MATLAB environment) is discussed, starting from experimental measures from sensor devices, ending with the 2D visualization of targets movements over time and focusing mainly on detection and localization algorithms. Moreover, two different scenarios and both single and multiple target tracking are analyzed.

Multiplex network analysis with application to biological high-throughput data

In questa tesi vengono studiate alcune caratteristiche dei network a multiplex; in particolare l'analisi verte sulla quantificazione delle differenze fra i layer del multiplex. Le dissimilarita sono valutate sia osservando le connessioni di singoli nodi in layer diversi, sia stimando le diverse partizioni dei layer. Sono quindi introdotte alcune importanti misure per la caratterizzazione dei multiplex, che vengono poi usate per la costruzione di metodi di community detection . La quantificazione delle differenze tra le partizioni di due layer viene stimata utilizzando una misura di mutua informazione. Viene inoltre approfondito l'uso del test dell'ipergeometrica per la determinazione di nodi sovra-rappresentati in un layer, mostrando l'efficacia del test in funzione della similarita dei layer. Questi metodi per la caratterizzazione delle proprieta dei network a multiplex vengono applicati a dati biologici reali. I dati utilizzati sono stati raccolti dallo studio DILGOM con l'obiettivo di determinare le implicazioni genetiche, trascrittomiche e metaboliche dell'obesita e della sindrome metabolica. Questi dati sono utilizzati dal progetto Mimomics per la determinazione di relazioni fra diverse omiche. Nella tesi sono analizzati i dati metabolici utilizzando un approccio a multiplex network per verificare la presenza di differenze fra le relazioni di composti sanguigni di persone obese e normopeso.

Near Real-Time Detection Of Pipe Bursts in Water Distribution Systems

The research work presented in the thesis describes a new methodology for the automated near real-time detection of pipe bursts in Water Distribution Systems (WDSs). The methodology analyses the pressure/flow data gathered by means of SCADA systems in order to extract useful informations that go beyond the simple and usual monitoring type activities and/or regulatory reporting , enabling the water company to proactively manage the WDSs sections. The work has an interdisciplinary nature covering AI techniques and WDSs management processes such as data collection, manipulation and analysis for event detection. Indeed, the methodology makes use of (i) Artificial Neural Network (ANN) for the short-term forecasting of future pressure/flow signal values and (ii) Rule-based Model for bursts detection at sensor and district level. The results of applying the new methodology to a District Metered Area in Emilia- Romagna’s region, Italy have also been reported in the thesis. The results gathered illustrate how the methodology is capable to detect the aforementioned failure events in fast and reliable manner. The methodology guarantees the water companies to save water, energy, money and therefore enhance them to achieve higher levels of operational efficiency, a compliance with the current regulations and, last but not least, an improvement of customer service.

A Reliable Downscaling of ECG Signals for the Detection of T wave Heterogeneity Features

In cardiovascular disease the definition and the detection of the ECG parameters related to repolarization dynamics in post MI patients is still a crucial unmet need. In addition, the use of a 3D sensor in the implantable medical devices would be a crucial mean in the assessment or prediction of Heart Failure status, but the inclusion of such feature is limited by hardware and firmware constraints. The aim of this thesis is the definition of a reliable surrogate of the 500 Hz ECG signal to reach the aforementioned objective. To evaluate the worsening of reliability due to sampling frequency reduction on delineation performance, the signals have been consecutively down sampled by a factor 2, 4, 8 thus obtaining the ECG signals sampled at 250, 125 and 62.5 Hz, respectively. The final goal is the feasibility assessment of the detection of the fiducial points in order to translate those parameters into meaningful clinical parameter for Heart Failure prediction, such as T waves intervals heterogeneity and variability of areas under T waves. An experimental setting for data collection on healthy volunteers has been set up at the Bakken Research Center in Maastricht. A 16 – channel ambulatory system, provided by TMSI, has recorded the standard 12 – Leads ECG, two 3D accelerometers and a respiration sensor. The collection platform has been set up by the TMSI property software Polybench, the data analysis of such signals has been performed with Matlab. The main results of this study show that the 125 Hz sampling rate has demonstrated to be a good candidate for a reliable detection of fiducial points. T wave intervals proved to be consistently stable, even at 62.5 Hz. Further studies would be needed to provide a better comparison between sampling at 250 Hz and 125 Hz for areas under the T waves.

Analysis of Local Search Methods for 3D Data

In questa tesi sono stati analizzati alcuni metodi di ricerca per dati 3D. Viene illustrata una panoramica generale sul campo della Computer Vision, sullo stato dell’arte dei sensori per l’acquisizione e su alcuni dei formati utilizzati per la descrizione di dati 3D. In seguito è stato fatto un approfondimento sulla 3D Object Recognition dove, oltre ad essere descritto l’intero processo di matching tra Local Features, è stata fatta una focalizzazione sulla fase di detection dei punti salienti. In particolare è stato analizzato un Learned Keypoint detector, basato su tecniche di apprendimento di machine learning. Quest ultimo viene illustrato con l’implementazione di due algoritmi di ricerca di vicini: uno esauriente (K-d tree) e uno approssimato (Radial Search). Sono state riportate infine alcune valutazioni sperimentali in termini di efficienza e velocità del detector implementato con diversi metodi di ricerca, mostrando l’effettivo miglioramento di performance senza una considerabile perdita di accuratezza con la ricerca approssimata.

Deep Learning Architectures for time of arrival detection in Acoustic Emissions Monitoring

Acoustic Emission (AE) monitoring can be used to detect the presence of damage as well as determine its location in Structural Health Monitoring (SHM) applications. Information on the time difference of the signal generated by the damage event arriving at different sensors is essential in performing localization. This makes the time of arrival (ToA) an important piece of information to retrieve from the AE signal. Generally, this is determined using statistical methods such as the Akaike Information Criterion (AIC) which is particularly prone to errors in the presence of noise. And given that the structures of interest are surrounded with harsh environments, a way to accurately estimate the arrival time in such noisy scenarios is of particular interest. In this work, two new methods are presented to estimate the arrival times of AE signals which are based on Machine Learning. Inspired by great results in the field, two models are presented which are Deep Learning models - a subset of machine learning. They are based on Convolutional Neural Network (CNN) and Capsule Neural Network (CapsNet). The primary advantage of such models is that they do not require the user to pre-define selected features but only require raw data to be given and the models establish non-linear relationships between the inputs and outputs. The performance of the models is evaluated using AE signals generated by a custom ray-tracing algorithm by propagating them on an aluminium plate and compared to AIC. It was found that the relative error in estimation on the test set was < 5% for the models compared to around 45% of AIC. The testing process was further continued by preparing an experimental setup and acquiring real AE signals to test on. Similar performances were observed where the two models not only outperform AIC by more than a magnitude in their average errors but also they were shown to be a lot more robust as compared to AIC which fails in the presence of noise.

Automatic detection of the inferior alveolar nerve in CT scans with CenterNet

The inferior alveolar nerve (IAN) lies within the mandibular canal, named inferior alveolar canal in literature. The detection of this nerve is important during maxillofacial surgeries or for creating dental implants. The poor quality of cone-beam computed tomography (CBCT) and computed tomography (CT) scans and/or bone gaps within the mandible increase the difficulty of this task, posing a challenge to human experts who are going to manually detect it and resulting in a time-consuming task.Therefore this thesis investigates two methods to automatically detect the IAN: a non-data driven technique and a deep-learning method. The latter tracks the IAN position at each frame leveraging detections obtained with the deep neural network CenterNet, fined-tuned for our task, and temporal and spatial information.

Model-Based validation of Driver Drowsiness Detection System for ADAS

The work described in this Master’s Degree thesis was born after the collaboration with the company Maserati S.p.a, an Italian luxury car maker with its headquarters located in Modena, in the heart of the Italian Motor Valley, where I worked as a stagiaire in the Virtual Engineering team between September 2021 and February 2022. This work proposes the validation using real-world ECUs of a Driver Drowsiness Detection (DDD) system prototype based on different detection methods with the goal to overcome input signal losses and system failures. Detection methods of different categories have been chosen from literature and merged with the goal of utilizing the benefits of each of them, overcoming their limitations and limiting as much as possible their degree of intrusiveness to prevent any kind of driving distraction: an image processing-based technique for human physical signals detection as well as methods based on driver-vehicle interaction are used. A Driver-In-the-Loop simulator is used to gather real data on which a Machine Learning-based algorithm will be trained and validated. These data come from the tests that the company conducts in its daily activities so confidential information about the simulator and the drivers will be omitted. Although the impact of the proposed system is not remarkable and there is still work to do in all its elements, the results indicate the main advantages of the system in terms of robustness against subsystem failures and signal losses.