For several years, Security Operation Centers (SOCs) have relied on tools such as Security Information and Event Management (SIEM) and Intrusion Detection Systems (IDS) for reactive threat detection and risk management. However, these tools are becoming inadequate in detecting the current threat landscape, which is continuously increasing in terms of volume and variety, and targeting the most vulnerable component in the kill-chain, the human actor. This manuscript presents a novel data-driven approach that models user and entity behaviour in the early stages of the kill-chain. The proposed system estimates the probability of an entity being exposed by a threat actor during the delivery stage, thereby providing better anticipation time allowing the end-user to undertake mitigation focusing on concrete entities. Moreover, the framework has been tested in a real-life scenario executing different realistic phishing simulations and achieving successful results.

Population aging in developed countries brings an increased prevalence of chronic disease and of polymedication-patients with several prescribed types of medication. Attention to chronic, polymedicated patients is a priority for its high cost and the associated risks, and tools for analyzing, understanding, and managing this reality are becoming necessary. We describe a prototype of a system for discovering, analyzing, and visualizing the co-occurrence of diagnostics, interventions, and medication prescriptions in a large patient database. The final tool is intended to be used both by health managers and planners and for primary care clinicians in direct contact with patients (for example for detecting unusual disease patterns and incorrect or missing medication). At the core of the analysis module there is a representation of diagnostics and medications as a hypergraph, and the most crucial functionalities rely on hypergraph transversal/variants of association rule discovery methods, with particular emphasis on discovering surprising or alarming combinations. The test database comes from the primary care system in the area of Barcelona for 2013, with over 1.6 million potential patients and almost 20 million diagnostics and prescriptions.

The dramatic rise in the use of social network platforms such as Facebook or Twitter has resulted in the availability of vast and growing user-contributed repositories of data. Exploiting this data by extracting useful information from it has become a great challenge in data mining and knowledge discovery. A recently popular way of extracting useful information from social network platforms is to build indicators, often in the form of a time series, of general public mood by means of sentiment analysis. Such indicators have been shown to correlate with a diverse variety of phenomena. In this article we follow this line of work and set out to assess, in a rigorous manner, whether a public sentiment indicator extracted from daily Twitter messages can indeed improve the forecasting of social, economic, or commercial indicators. To this end we have collected and processed a large amount of Twitter posts from March 2011 to the present date for two very different domains: stock market and movie box office revenue . For each of these domains, we build and evaluate forecasting models for several target time series both using and ignoring the Twitter-related data. If Twitter does help, then this should be reflected in the fact that the predictions of models that use Twitter-related data are better than the models that do not use this data. By systematically varying the models that we use and their parameters, together with other tuning factors such as lag or the way in which we build our Twitter sentiment index, we obtain a large dataset that allows us to test our hypothesis under different experimental conditions. Using a novel decision-tree-based technique that we call summary tree we are able to mine this large dataset and obtain automatically those configurations that lead to an improvement in the prediction power of our forecasting models. As a general result, we have seen that nonlinear models do take advantage of Twitter data when forecasting trends in volatility indices, while linear ones fail systematically when forecasting any kind of financial time series. In the case of predicting box office revenue trend, it is support vector machines that make best use of Twitter data. In addition, we conduct statistical tests to determine the relation between our Twitter time series and the different target time series.

In many practical applications, one is interested in generating a ranked list of items using information mined from continuous streams of data. For example, in the context of computer networks, one might want to generate lists of nodes ranked according to their susceptibility to attack. In addition, real-world data streams often exhibit concept drift, making the learning task even more challenging. We present an online learning approach to ranking with concept drift, using weighted majority techniques. By continuously modeling different snapshots of the data and tuning our measure of belief in these models over time, we capture changes in the underlying concept and adapt our predictions accordingly. We measure the performance of our algorithm on real electricity data as well as asynthetic data stream, and demonstrate that our approach to ranking from stream data outperforms previously known batch-learning methods and other online methods that do not account for concept drift.

This paper is concerned with compact routing schemes for arbitrary undirected networks in the name‐independent model first introduced by Awerbuch, Bar‐Noy, Linial, and Peleg. A compact routing scheme that uses local routing tables of size $\~{O}(n^{1/2})$, $O(\log^2 n)$‐sized packet headers, and stretch bounded by 5 is obtained, where n is the number of nodes in the network. (We use the notation $\~{O}\left(f(n)\right)$ to represent $O(f(n)\log^c{n})$, where c is an arbitrary nonnegative real number, independent of n.) Alternative schemes reduce the packet header size to $O(\log n)$ at the cost of either increasing the stretch to 7 or increasing the table size to $\~{O}(n^{2/3})$. For smaller table‐size requirements, the ideas in these schemes are generalized to a scheme that uses $O(\log^2 n)$‐sized headers and ${O}(k^2n^{2/k})$‐sized tables, and achieves a stretch of $\min\{1 + (k-1)(2^{k/2}-2), 16k^2-8k\}$, improving the best previously known name‐independent scheme due to Awerbuch and Peleg.

This paper presents compact roundtrip routing schemes with local tables of size Õ(√n) and stretch 6 for any directed network with arbitrary edge weights; and with local tables of size Õ(√−1n2/k) and stretch min((2k/2 −1)(k + √), 16k 2+ 8 k − 8), for any directed network with polynomially-sized edges, both in the topology-independent node-name model. These are the first topology-independent results that apply to routing in directed networks.

This paper is concerned with compact routing in the name independent model first introduced by Awerbuch et al. [1] for adaptive routing in dynamic networks. A compact routing scheme that uses local routing tables of size Õ(n1/2), O(log2 n)-sized packet headers, and stretch bounded by 5 is obtained. Alternative schemes reduce the packet header size to O(log n) at cost of either increasing the stretch to 7, or increasing the table size to Õ(n2/3). For smaller table-size requirements, the ideas in these schemes are generalized to a scheme that uses O(log2 n)-sized headers, Õ(k2n2/k)-sized tables, and achieves a stretch of min[1 + (k-1)(2k/2-2), 16k2+4k ], improving the best previously-known name-independent scheme due to Awerbuch and Peleg [3].