Computer Science - Doctoral Theses
Permanent URI for this collection
Browse
Recent Submissions
Item Modelling and enhanced scheduling in the cellular vehicular sidelink standards(University College Cork, 2024) McCarthy, Brian; O'Driscoll, Aisling; Sreenan, Cormac J.; Science Foundation IrelandVehicular networking can address significant challenges in the areas of vehicular safety, traffic efficiency, and enables higher levels of autonomous driving for sustainable mobility. The Third Generation Partnership Project (3GPP) Cellular Vehicle-To-Everything (C-V2X) standard and subsequent New Radio Vehicle-To-Everything (NR-V2X) standard are relatively new yet disruptive technology enablers in the regulatory landscape. Unfortunately, the relative infancy of the standards has resulted in shortcomings in their ability to effectively handle real-life vehicular service characteristics and network management techniques. Specifically, the scheduler that forms the basis of both C-V2X and NR-V2X cannot effectively schedule variable packet inter arrival rates, variable packet sizes or facilitate congestion control techniques. This thesis will address these challenges by providing a rigorous analysis of the scheduling problems caused by these contemporary vehicular applications, emphasising the complexity posed by European Telecommunications Standards Institute (ETSI) and 3GPP standard application models. It further addresses the pressing issue of congestion management within diverse and dense vehicular scenarios, all while preserving scheduling performance. Specifically, this thesis proposes, evaluates, and analyses solutions based on machine learning enabled prediction of inter packet arrival times, scheduler compliant congestion control mechanisms, and a deep understanding of the role of MCS adaptation in V2X scheduling.Item A cryptographic approach to location privacy(University College Cork, 2023) Eshun, Samuel N.; Palmieri, PaoloThe rapid expansion of location-based services (LBS) has driven an escalating demand for personalised and context-aware applications, enriching user experiences across health, weather, and navigation sectors. These services offer valuable insights into various applications using large-scale datasets of individual mobility traces. However, alongside the benefits come considerable privacy concerns, as the data could inadvertently reveal sensitive information about users' movements and behaviours. This thesis delves into multiple facets of privacy within LBS, concentrating on the de-anonymisation of mobility data and the subsequent privacy risks it poses. In response to these concerns, the thesis presents privacy-preserving indoor localisation techniques, later improved with an efficient cryptographic protocol to protect users and service providers against privacy breaches. The first part of this thesis focuses on de-anonymisation attacks on mobility data. We propose a novel de-anonymisation model that employs hidden Markov models (HMM) to create user mobility profiles based on spatiotemporal trajectories. The performance of this model is assessed using real-world mobility datasets from two different cities, Shanghai and Rome. Our attack techniques significantly improve over existing de-anonymisation techniques, successfully re-identifying up to 85% and 90% of anonymised users in the respective datasets. However, despite the model's effectiveness, limitations exist, such as the model's dependence on the availability of a training dataset. Future work could explore unsupervised machine learning algorithms to address these limitations or utilise more sophisticated techniques like recurrent neural networks (RNNs) to model the evolution of user mobility behaviour over time. The second part of the thesis addresses privacy concerns in indoor Wi-Fi localisation. We propose a privacy-preserving protocol that uses partial homomorphic encryption (Paillier's cryptosystem) to guarantee user location privacy while allowing computation in the encrypted domain. This approach ensures that most of the computational overhead on the user side is delegated to the server while hiding the user's exact location. By leveraging the Spatial Bloom filter {data structure}, complemented by homomorphic encryption, the service provider can learn about the user's presence in predefined areas without revealing the user's exact location or these predefined areas to the user. The third part of the thesis introduces an efficient and privacy-preserving cryptographic protocol that incorporates a more realistic security assumption in the form of a malicious adversary, one of the most important improvements to guarantee privacy for both the service provider and the user, unlike the semi-honest adversary in the previous protocol. Our protocol employs additive homomorphic encryption (DGK encryption) to preserve the privacy of the user's location fingerprint while allowing the service provider to compute over the encrypted fingerprint. In addition, garbled circuits protect the service provider's reference database against malicious users while delivering location output to the user. Finally, spatial Bloom filters further enhance the protocol by allowing the service provider to learn the user's vicinity in predefined areas of interest without revealing the exact location to the user or these predefined areas. Compared to similar protocols, our proposed solution demonstrates a significant reduction in computational costs on the user side and a 99.99% reduction in online communication costs, making it more efficient and practicable in the Internet of Things environments. Furthermore, our protocol is the first to provide security against malicious users, whereas other protocols are limited to honest-but-curious adversaries. For future work, we recommend strengthening the protection against actively corrupt service providers or cloud services by implementing additional cryptographic techniques, such as the ABY framework, for efficient mixed-protocol multiparty computation. Moreover, exploring other protocols or cryptographic primitives that improve efficiency, security, and privacy is encouraged, possibly through the combination of different techniques to optimise the protocol's current efficiency or reduce the size of the garbled circuit. By examining the challenges posed by de-anonymisation attacks and developing innovative solutions, this thesis offers a comprehensive approach to enhancing privacy and security in location-based services. By investigating privacy-preserving indoor localisation techniques and developing efficient protocols, we strive to protect the interests of both users and service providers. As the demand for personalised and context-aware applications continues to grow, this research contributes significantly to the ongoing conversation surrounding privacy and data protection in the digital age. The importance of addressing privacy concerns in location-based services cannot be overstated. As technological advancements progress and LBS permeate various aspects of our lives, ensuring the confidentiality of user data becomes paramount. The solutions presented in this thesis, including privacy-preserving indoor localisation techniques and efficient cryptographic protocols, are crucial steps towards achieving a balance between the benefits offered by these services and the privacy requirements of users and service providers. As location-based services evolve, new challenges and privacy risks will undoubtedly emerge. Therefore, the work presented in this thesis should be considered part of an ongoing effort to develop and refine techniques that preserve user privacy while maintaining the functionality and efficiency of LBS. The exploration of alternative cryptographic primitives, the improvement of existing protocols, and the development of new privacy-preserving methods will be essential to ensuring the continued growth and success of location-based services in a secure and privacy-conscious manner. In conclusion, this thesis comprehensively examines privacy concerns in LBS, focusing on de-anonymising mobility data and developing privacy-preserving indoor localisation techniques. The efficient cryptographic protocols proposed to offer robust protection for both users and service providers, paving the way for a more secure and privacy-oriented future for LBS.Item Intelligibility of music playlists(University College Cork, 2023) Gabbolini, Giovanni; Bridge, Derek G.; Science Foundation IrelandA common strategy for organising music is by arranging songs in a playlist to obtain a continuous and thematic music flow. Playlists are popular in music streaming services, where 58% of the listeners construct their own playlists. The flip side of popularity is content-overload; streaming services currently host billions of playlists. The commercial value of playlists has attracted notable research efforts during the last two decades. Much of the research on playlists is concerned with automatically constructing playlists. This dissertation is on playlists, but on a topic complementary to constructing playlists. Our concern here is on describing playlists, so that playlists can be understood by a human audience, i.e. so that they become intelligible. The way we achieve intelligibility is by developing algorithms that can generate textual annotations, both at playlist level and at song level. At playlist level, an annotation can be text (e.g. a tag or a caption) that describes the playlist as a whole; at song level, an annotation can be text that describes the transition between two consecutive songs in the playlist. The purpose of intelligibility is that of facilitating music organisation & access, as well as enhancing the listen- ing experience of users, two goals particularly relevant in a content overload scenario. We propose five algorithms for playlist-level intelligibility, and three algorithms for song-level intelligibility. We are particularly interested in the user experi- ence, so we test the algorithms, in most cases, with both offline experiments and user trials. We find evidence that the algorithms can help accomplish the two goals of intelligibility, i.e. enhancing listening experiences, and facilitating organisation and access. We pair the algorithms with a comprehensive survey of MIR research on music playlists, which provide a useful framework for understanding our contributions in the context of a broad selection of related research.Item Leveraging network state for software-defined data centre network management(University College Cork, 2023) Sherwin, Jonathan; Sreenan, Cormac J.; Munster Technological UniversityThis work addresses key aspects in the management of a software-defined multi-tenant Data Centre Network (DCN). Software-defined networking (SDN) offers significant potential benefit for many aspects of DCN management – e.g. configuration, monitoring, performance and utilisation, and security – and many researchers have worked, successfully, over the last number of years to show how improvements to these areas could be achieved. The insight that motivated this work is that the focus by researchers and tool vendors has been on managing the current state or desired future state of the DCN. Meanwhile, issues relating to reviewing, analysing and evaluating the past state of a software-defined DCN have been neglected. SDN has been essential for DCNs to meet the requirements of a multi-tenant cloud environment - through automated, dynamic reconfiguration of network devices and services to accommodate tenants arriving, leaving, and modifying their resource requirements via a self-service interface. Consequently, a DCN operator cannot be expected to know the current state of the network, let alone past states, without tools to query the network and provide that information. DCN operators are well served by tools to manage and query the current state of an SDN, but not previous network states and events. The research question addressed in this work is how to record the topological and configuration history of a DCN, present a useful view of that historical record to the DCN operator, and provide the means for the operator to query the historical DCN state. A related question is how to employ SDN itself to improve the performance of a software-defined DCN. Solving these issues is challenging because of the scale of a DCN (potentially scaling to hundreds of switches connecting thousands of devices), the constantly changing configuration of a multi-tenant software-defined DCN, and the duration of months or years over which the history must be recorded, analysed and available for querying. The selected approach takes advantage of the decoupled nature of the control- and data-planes in SDN, to eavesdrop on communications between an SDN controller and switches. Emulated and conceptual models of a DCN have been created from key information extracted from the captured communications. The conceptual model relies on a combination of new and existing ontologies, with an extensible set of concepts and relationships that are the target of complex operator-focussed queries. The contributions of the work are as follows: 1. Accurate reproduction of an emulated copy of a DCN (topology and state) for any time in its history solely from a passively captured log of control-plane messages. 2. The use of snapshots to speed up the reproduction time of an emulated DCN with topology and state for a particular point in time. 3. Use of an ontological approach to creating a temporal and topological model of a DCN, populated solely from a log of control-plane messages, and created for the purpose of answering operator queries. 4. A methodology to develop additional sophisticated queries against the ontological model regarding the historical state of and events on a DCN. 5. A method to improve the veracity of control-plane messages by reducing the latency of interactions between SDN controllers and hardware switches in a DCN.Item Metaheuristics and machine learning for joint stratification and sample allocation in survey design(University College Cork, 2022-01) O'Luing, Mervyn; Prestwich, Steve; Tarim, Armagan; European Regional Development Fund; Science Foundation IrelandIn this thesis, we propose a number of metaheuristics and machine learning techniques to solve the joint stratification and sample allocation problem. Finding the optimal solution to this problem is hard when the sampling frame is large, and the evaluation algorithm is computationally burdensome. To advance the research in this area, we explore and evaluate different algorithmic methods of modelling and solving this problem. Firstly, we propose a new genetic algorithm approach using "grouping" genetic operators instead of traditional operators. Experiments show a significant improvement in solution quality for similar computational effort. Next, we combine the capability of a simulated annealing algorithm to escape from local minima with delta evaluation to exploit the similarity between consecutive solutions and thereby reduce evaluation time. Comparisons with two recent algorithms show the simulated annealing algorithm attaining comparable solution qualities in less computation time. Then, we consider the combination of the k-means and clustering algorithms with a hill climbing algorithm in stages and report the solution costs, evaluation times and training times. The multi-stage combinations generally compare well with recent algorithms, and provide the survey designer with a greater choice of algorithms to choose from. Finally, we combine the explorative properties of an estimation of distribution algorithm (EDA) to model the probabilities of an atomic stratum belonging to different strata with the exploitative search properties of a simulated annealing algorithm to create a hybrid estimation of distribution algorithm (HEDA). Results of comparisons with the best solution qualities from our earlier experiments show that the HEDA finds better solution qualities, but requires a longer total execution time than alternative approaches we considered.