In today’s digital landscape, users frequently share vast amounts of information, including confidential data, often without full awareness of the associated privacy risks. This scenario highlights the need for automated methods to identify sensitive information and alert users to such risks. Existing algorithmic solutions for detecting sensitive content typically require either human intervention (rule-based approaches) or labeled data (supervised learning), both of which can be costly and limiting. In this paper, we propose a framework based on Retrieval-Augmented Generation (RAG) to classify privacy-sensitive content while providing contextual explanations. We employed the state-of-the-art generative Large Language Model (LLM) GPT-4o, with Information Retrieval models BM25 and FAISS, enhancing both detection accuracy and explainability. Our method utilizes a curated Knowledge Base of scientific literature on privacy and confidentiality to retrieve contextually relevant information, which is then used to guide the classification process and generate explanations. Experimental evaluations on a real-world dataset (Enron Email Dataset) demonstrate that RAG-based approaches significantly outperform the zero-shot baseline, with BM25 showing the highest performance. This tool is designed to serve end-users, by mitigating risks before data sharing, by enabling proactive monitoring of privacy violations.

The availability of a multitude of data sources has naturally increased the need for subjects to collaborate for supporting distributed computations that combine different data collections for their elaboration and analysis. Due to the quick pace at which datasets grow, often the authorities collecting and owning such datasets resort to external third parties (e.g., cloud providers) for their storage and management. Data under the control of different authorities are autonomously encrypted (using different encryption schemes and keys) for their external storage. This makes distributed computations combining these sources difficult to support. In this paper, we propose an approach enabling collaborative computations over data encrypted in storage, selectively involving also subjects that might not be authorized for accessing the data in plaintext when their collaboration is considered economically convenient. We also consider the possible adoption of trusted hardware components, to enable the evaluation of operations over plaintext data at non-fully trusted computational providers. The experimental results confirm the economic benefits that can be enabled by our proposal.

$\kappa $-Anonymity and$\ell $-diversity are two well-known privacy metrics that guarantee protection of the respondents of a dataset by obfuscating information that can disclose their identities and sensitive information. Existing solutions for enforcing them implicitly assume to operate in a centralized scenario, since they require complete visibility over the dataset to be anonymized, and can therefore have limited applicability in anonymizing large datasets. In this paper, we propose a solution that extends Mondrian (an efficient and effective approach designed for achieving$\kappa $-anonymity) for enforcing both$\kappa $-anonymity and$\ell $-diversity over large datasets in a distributed manner, leveraging the parallel computation of multiple workers. Our approach efficiently distributes the computation among the workers, without requiring visibility over the dataset in its entirety. Our data partitioning limits the need for workers to exchange data, so that each worker can independently anonymize a portion of the dataset. We implemented our approach providing parallel execution on a dynamically chosen number of workers. The experimental evaluation shows that our solution provides scalability, while not affecting the quality of the resulting anonymization.

The combined adoption of selective encryption and smart contracts deployed on blockchains allows data owners to maintain control over their data when traded on digital data market platforms.Selective encryption, combined with key derivation techniques, guarantees that only customers who are entitled to access a resource can read its content.The adoption of smart contracts deployed on a blockchain permits to regulate the interplay among parties, the possible economic incentives to be paid to the owners, and the exchange of the information necessary for resource decryption (i.e., updates to the key derivation structure) upon payment.However, operations on blockchains have a cost.In this paper, we propose two approaches for updating the key derivation structure to enable customers to access resources, while limiting access times to resources and the cost of write operations on the blockchain to enforce purchases.

When moving large and heterogeneous data collections to the cloud, a key requirement concerns the selection of the most suitable (set of) cloud service(s) for outsourcing. Not only can different resources have different characteristics and requirements, but different cloud providers can also offer different services and security guarantees, and can have different costs. Selecting a single service for outsourcing an entire data collection can result in a non-optimal solution, as a single service satisfying, at reasonable costs, all the requirements specified by the data owner might not exist. Selecting a set of services could instead ensure the satisfaction of the requirements, possibly with economic advantages. In this article, we address this problem and present a flexible and expressive, yet simple model for supporting data owners in identifying a proper allocation of their resources to a set of cloud services. Our model allows data owners to specify in an easy and intuitive way protection requirements operating at the granularity level of single resource (or class thereof), and representing the minimum security guarantees that a cloud service must offer to store resources. Resources can be outsourced in plaintext or encrypted form, depending on their requirements and on what is the most convenient allocation. Data owners can then also specify global allocation requirements that apply to the overall allocation, to reduce the burden on their side and to avoid excessive fragmentation of the resource collection. We solve the problem of finding an allocation that satisfies both the protection and the global allocation requirements, while minimizing economic costs, by formulating it as a binary programming problem, thus allowing the use of existing techniques for its efficient solution.

With the cloud emerging as a successful paradigm for conveniently storing, accessing, processing, and sharing information, the cloud market has seen an incredible growth. An ever-increasing number of providers offer today several cloud plans, with different guarantees in terms of service properties such as performance, cost, or security. While such a variety naturally corresponds to a diversified user demand, it is far from trivial for users to identify the cloud providers and plans that better suit their specific needs. In this paper, we address the problem of supporting users in cloud plan selection. We characterize different kinds of requirements that may need to be supported in cloud plan selection and introduce a very simple and intuitive, yet expressive, language that captures different requirements as well as preferences users may wish to express. The corresponding formal modeling permits to reason on requirements satisfaction to identify plans that meet the constraints imposed by requirements, and to produce a preference-based ranking among such plans.

We propose an approach for allowing data owners to trade their data in digital data market scenarios, while keeping control over them. Our solution is based on a combination of selective encryption and smart contracts deployed on a blockchain, and ensures that only authorized users who paid an agreed amount can access a data item. We propose a safe interaction protocol for regulating the interplay between a data owner and subjects wishing to purchase (a subset of) her data, and an audit process for counteracting possible misbehaviors by any of the interacting parties. Our solution aims to make a step towards the realization of data market platforms where owners can benefit from trading their data while maintaining control.

Recent ICTs paradigms such as cloud computing, data outsourcing, digital data markets, and the spread of multiple social media based on Web 2.0 technologies, facilitate the exchange of large data and information flows among a myriad of interconnected devices and users, for different aims and purposes. This complex scenario underlies the development of on-line ecosystems of interacting entities, where the concepts of community, self-organization, evolution and knowledge are fundamental.

We present a novel approach for the specification and enforcement of authorizations that enables controlled data sharing for collaborative queries in the cloud. Data authorities can establish authorizations regulating access to their data distinguishing three visibility levels (no visibility, encrypted visibility, and plaintext visibility). Authorizations are enforced in the query execution by possibly restricting operation assignments to other parties and by adjusting visibility of data on-the-fly. Our approach enables users and data authorities to fully enjoy the benefits and economic savings of the competitive open cloud market, while maintaining control over data.

Data fragmentation has been proposed as a solution for protecting the confidentiality of sensitive associations when releasing data for publishing or external storage. To enrich the utility of data fragments, a recent approach has put forward the idea of complementing a pair of fragments with some (non-precise, hence loose) information on the association between them. Starting from the observation that in presence of multiple fragments the publication of several independent associations between pairs of fragments can cause improper leakage of sensitive information, in this paper we extend loose associations to operate over an arbitrary number of fragments. We first illustrate how the publication of multiple loose associations between different pairs of fragments can potentially expose sensitive associations, and describe an approach for defining loose associations among an arbitrary set of fragments. We investigate how tuples in fragments can be grouped for producing loose associations so to increase the utility of queries executed over fragments. We then provide a heuristics for performing such a grouping and producing loose associations satisfying a given level of protection for sensitive associations, while achieving utility for queries over different fragments. We also illustrate the result of an extensive experimental effort over both synthetic and real datasets, which shows the efficiency and the enhanced utility provided by our proposal.

Fragmentation has been recently proposed as a promising approach to protect the confidentiality of sensitive associations whenever data need to undergo external release or storage. By splitting attributes among different fragments, fragmentation guarantees confidentiality of the associations among these attributes under the assumption that such associations cannot be reconstructed by re-combining the fragments. We note that the requirement that fragments do not have attributes in common, imposed by previous proposals, is only a necessary, but not sufficient, condition to ensure that information in different fragments cannot be recombined as dependencies may exist among data enabling some form of linkability. In this paper, we identify the problem of improper information leakage due to data dependencies, provide a formulation of the problem based on a natural graphical modeling, and present an approach to tackle it in an efficient and scalable way.

The proper protection of data privacy is a complex task that requires a careful analysis of what actually has to be kept private. Several definitions of privacy have been proposed over the years, from traditional syntactic privacy definitions, which capture the protection degree enjoyed by data respondents with a numerical value, to more recent semantic privacy definitions, which take into consideration the mechanism chosen for releasing the data. In this paper, we illustrate the evolution of the definitions of privacy, and we survey some data protection techniques devised for enforcing such definitions. We also illustrate some well-known application scenarios in which the discussed data protection techniques have been successfully used, and present some open issues.

Data sharing and dissemination are becoming increasingly important for conducting our daily life activities. The main consequence of this trend is that huge collections of data are easily available and accessible, leading to growing privacy concerns. The research community has devoted many efforts aiming at addressing the complex privacy requirements that characterize the modern Information Society. Although several advancements have been made, still many open issues need to be investigated. In this paper, we consider a scenario where data are incrementally released and we address the privacy problem arising when sensitive non released properties depend on (and can therefore be inferred from) non-sensitive released data. We propose a model capturing this inference problem, where sensitive information is characterized by peculiar value distributions of non sensitive released data. We then describe how to counteract possible inferences that an observer can draw by applying different statistical metrics on released data. Finally, we perform an experimental evaluation of our solution, showing its efficacy.

With the growing needs for data sharing and dissemination, privacy-preserving data publishing is becoming an important issue that still requires further investigation. In this paper, we make a step towards private data publication by proposing a solution based on the release of vertical views (frag ments) over a relational table that satisfy confidentiality and visibility constraints expressing requirements for information protection and release, respectively. We translate the problem of computing a fragmentation composed of the minimum number of fragments into the problem of computing a maximum weighted clique over a fragmentation graph. The fragmentation graph models fragments, efficiently computed using Ordered Binary Decision Diagrams (OBDDs), that satisfy all the confidentiality constraints and a subset of the visibility constraints defined in the system. We then show an exact and a heuristic algorithm for computing a minimal and a locally minimal fragmentation, respectively. Finally, we provide experimental results comparing the execution time and the fragmentations returned by the exact and heuristic algorithms. The experiments show that the heuristic algorithm has low computation cost and computes a fragmentation close to optimum.