Biblio

Vector space models (VSMs) are mathematically well-defined frameworks that have been widely used in text processing. In these models, high-dimensional, often sparse vectors represent text units. In an application, the similarity of vectors -- and hence the text units that they represent -- is computed by a distance formula. The high dimensionality of vectors, however, is a barrier to the performance of methods that employ VSMs. Consequently, a dimensionality reduction technique is employed to alleviate this problem. This paper introduces a new method, called Random Manhattan Indexing (RMI), for the construction of L1 normed VSMs at reduced dimensionality. RMI combines the construction of a VSM and dimension reduction into an incremental, and thus scalable, procedure. In order to attain its goal, RMI employs the sparse Cauchy random projections.

Formal methods, models and tools for social big data analytics are largely limited to graph theoretical approaches such as social network analysis (SNA) informed by relational sociology. There are no other unified modeling approaches to social big data that integrate the conceptual, formal and software realms. In this paper, we first present and discuss a theory and conceptual model of social data. Second, we outline a formal model based on set theory and discuss the semantics of the formal model with a real-world social data example from Facebook. Third, we briefly present and discuss the Social Data Analytics Tool (SODATO) that realizes the conceptual model in software and provisions social data analysis based on the conceptual and formal models. Fourth and last, based on the formal model and sentiment analysis of text, we present a method for profiling of artifacts and actors and apply this technique to the data analysis of big social data collected from Facebook page of the fast fashion company, H&M.
 

Contingency analysis is a critical activity in the context of the power infrastructure because it provides a guide for resiliency and enables the grid to continue operating even in the case of failure. In this paper, we augment this concept by introducing SOCCA, a cyber-physical security evaluation technique to plan not only for accidental contingencies but also for malicious compromises. SOCCA presents a new unified formalism to model the cyber-physical system including interconnections among cyber and physical components. The cyber-physical contingency ranking technique employed by SOCCA assesses the potential impacts of events. Contingencies are ranked according to their impact as well as attack complexity. The results are valuable in both cyber and physical domains. From a physical perspective, SOCCA scores power system contingencies based on cyber network configuration, whereas from a cyber perspective, control network vulnerabilities are ranked according to the underlying power system topology.
 

Being the most important critical infrastructure in Cyber-Physical Systems (CPSs), a smart grid exhibits the complicated nature of large scale, distributed, and dynamic environment. Taxonomy of attacks is an effective tool in systematically classifying attacks and it has been placed as a top research topic in CPS by a National Science Foundation (NSG) Workshop. Most existing taxonomy of attacks in CPS are inadequate in addressing the tight coupling of cyber-physical process or/and lack systematical construction. This paper attempts to introduce taxonomy of attacks of agent-based smart grids as an effective tool to provide a structured framework. The proposed idea of introducing the structure of space-time and information flow direction, security feature, and cyber-physical causality is innovative, and it can establish a taxonomy design mechanism that can systematically construct the taxonomy of cyber attacks, which could have a potential impact on the normal operation of the agent-based smart grids. Based on the cyber-physical relationship revealed in the taxonomy, a concrete physical process based cyber attack detection scheme has been proposed. A numerical illustrative example has been provided to validate the proposed physical process based cyber detection scheme.
 

Tracking moving objects is a task of the utmost importance to the defence community. As this task requires high accuracy, rather than employing a single detector, it has become common to use multiple ones. In such cases, the tracks produced by these detectors need to be correlated (if they belong to the same sensing modality) or associated (if they were produced by different sensing modalities). In this work, we introduce Computational-Intelligence-based methods for correlating and associating various contacts and tracks pertaining to maritime vessels in an area of interest. Fuzzy k-Nearest Neighbours will be used to conduct track correlation and Fuzzy C-Means clustering will be applied for association. In that way, the uncertainty of the track correlation and association is handled through fuzzy logic. To better model the state of the moving target, the traditional Kalman Filter will be extended using an Echo State Network. Experimental results on five different types of sensing systems will be discussed to justify the choices made in the development of our approach. In particular, we will demonstrate the judiciousness of using Fuzzy k-Nearest Neighbours and Fuzzy C-Means on our tracking system and show how the extension of the traditional Kalman Filter by a recurrent neural network is superior to its extension by other methods.

Due to deep automation, the configuration of many Cloud infrastructures is static and homogeneous, which, while easing administration, significantly decreases a potential attacker's uncertainty on a deployed Cloud-based service and hence increases the chance of the service being compromised. Moving-target defense (MTD) is a promising solution to the configuration staticity and homogeneity problem. This paper presents our findings on whether and to what extent MTD is effective in protecting a Cloud-based service with heterogeneous and dynamic attack surfaces - these attributes, which match the reality of current Cloud infrastructures, have not been investigated together in previous works on MTD in general network settings. We 1) formulate a Cloud-based service security model that incorporates Cloud-specific features such as VM migration/snapshotting and the diversity/compatibility of migration, 2) consider the accumulative effect of the attacker's intelligence on the target service's attack surface, 3) model the heterogeneity and dynamics of the service's attack surfaces, as defined by the (dynamic) probability of the service being compromised, as an S-shaped generalized logistic function, and 4) propose a probabilistic MTD service deployment strategy that exploits the dynamics and heterogeneity of attack surfaces for protecting the service against attackers. Through simulation, we identify the conditions and extent of the proposed MTD strategy's effectiveness in protecting Cloud-based services. Namely, 1) MTD is more effective when the service deployment is dense in the replacement pool and/or when the attack is strong, and 2) attack-surface heterogeneity-and-dynamics awareness helps in improving MTD's effectiveness.

Intrusion response is a new generation of technology basing on active defence idea, which has very prominent significance on the protection of network security. However, the existing automatic intrusion response systems are difficult to judge the real "danger" of invasion or attack. In this study, an immune-inspired adaptive automated intrusion response system model, named as AIAIM, was given. With the descriptions of self, non-self, memory detector, mature detector and immature detector of the network transactions, the real-time network danger evaluation equations of host and network are built up. Then, the automated response polices are taken or adjusted according to the real-time danger and attack intensity, which not only solve the problem that the current automated response system models could not detect the true intrusions or attack actions, but also greatly reduce the response times and response costs. Theory analysis and experimental results prove that AIAIM provides a positive and active network security method, which will help to overcome the limitations of traditional passive network security system.
 

Variable Precision Rough Set (VPRS) model is one of the most important extensions of the Classical Rough Set (RS) theory. It employs a majority inclusion relation mechanism in order to make the Classical RS model become more fault tolerant, and therefore the generalization of the model is improved. This paper can be viewed as an extension of previous investigations on attribution reduction problem in VPRS model. In our investigation, we illustrated with examples that the previously proposed reduct definitions may spoil the hidden classification ability of a knowledge system by ignoring certian essential attributes in some circumstances. Consequently, by proposing a new β-consistent notion, we analyze the relationship between the structures of Decision Table (DT) and different definitions of reduct in VPRS model. Then we give a new notion of β-complement reduct that can avoid the defects of reduct notions defined in previous literatures. We also supply the method to obtain the β- complement reduct using a decision table splitting algorithm, and finally demonstrate the feasibility of our approach with sample instances.
 

By representing large corpora with concise and meaningful elements, topic-based generative models aim to reduce the dimension and understand the content of documents. Those techniques originally analyze on words in the documents, but their extensions currently accommodate meta-data such as authorship information, which has been proved useful for textual modeling. The importance of learning authorship is to extract author interests and assign authors to anonymous texts. Author-Topic (AT) model, an unsupervised learning technique, successfully exploits authorship information to model both documents and author interests using topic representations. However, the AT model simplifies that each author has equal contribution on multiple-author documents. To overcome this limitation, we assumes that authors give different degrees of contributions on a document by using a Dirichlet distribution. This automatically transforms the unsupervised AT model to Supervised Author-Topic (SAT) model, which brings a novelty of authorship prediction on anonymous texts. The SAT model outperforms the AT model for identifying authors of documents written by either single authors or multiple authors with a better Receiver Operating Characteristic (ROC) curve and a significantly higher Area Under Curve (AUC). The SAT model not only achieves competitive performance to state-of-the-art techniques e.g. Random forests but also maintains the characteristics of the unsupervised models for information discovery i.e. Word distributions of topics, author interests, and author contributions.
 

In Wireless Mesh Networks (WMNs), Network-Wide Broadcasts (NWBs) are a fundamental operation, required by routing and other mechanisms that distribute information to all nodes in the network. However, due to the characteristics of wireless communication, NWBs are generally problematic. Optimizing them thus is a prime target when improving the overall performance and dependability of WMNs. Most existing optimizations neglect the real nature of WMNs and are based on simple graph models, which provide optimistic assumptions of NWB dissemination. On the other hand, models that fully consider the complex propagation characteristics of NWBs quickly become unsolvable due to their complexity. In this paper, we present the Monte Carlo method Probabilistic Breadth-First Search (PBFS) to approximate the reachability of NWB protocols. PBFS simulates individual NWBs on graphs with probabilistic edge weights, which reflect link qualities of individual wireless links in the WMN, and estimates reachability over a configurable number of simulated runs. This approach is not only more efficient than existing ones, but further provides additional information, such as the distribution of path lengths. Furthermore, it is easily extensible to NWB schemes other than flooding. The applicability of PBFS is validated both theoretically and empirically, in the latter by comparing reachability as calculated by PBFS and measured in a real-world WMN. Validation shows that PBFS quickly converges to the theoretically correct value and approximates the behavior of real-life testbeds very well. The feasibility of PBFS to support research on NWB optimizations or higher level protocols that employ NWBs is demonstrated in two use cases.

This paper presents the application of fusion meth- ods to a visual surveillance scenario. The range of relevant features for re-identifying vehicles is discussed, along with the methods for fusing probabilistic estimates derived from these estimates. In particular, two statistical parametric fusion methods are considered: Bayesian Networks and the Dempster Shafer approach. The main contribution of this paper is the development of a metric to allow direct comparison of the benefits of the two methods. This is achieved by generalising the Kelly betting strategy to accommodate a variable total stake for each sample, subject to a fixed expected (mean) stake. This metric provides a method to quantify the extra information provided by the Dempster-Shafer method, in comparison to a Bayesian Fusion approach. 

The paradigm shift from traditional BPM to Subject-oriented BPM (S-BPM) is accounted to identifying independently acting subjects. As such, they can perform arbitrary actions on arbitrary objects. Abstract State Machines (ASMs) work on a similar basis. Exploring their capabilities with respect to representing and executing S-BPM models strengthens the theoretical foundations of S-BPM, and thus, validity of S-BPM tools. Moreover it enables coherent intertwining of business process modeling with executing of S-BPM representations. In this contribution we introduce the framework and roadmap tackling the exploration of the ASM approach in the context of S-BPM. We also report the major result, namely the implementation of an executable workflow engine with an Abstract State Machine interpreter based on an existing abstract interpreter model for S-BPM (applying the ASM refinement concept). This workflow engine serves as a baseline and reference implementation for further language and processing developments, such as simulation tools, as it has been developed within the Open-S-BPM initiative.

Recent attention to aviation cyber physical systems (ACPS) is driven by the need for seamless integration of design disciplines that dominate physical world and cyber world convergence. System convergence is a big obstacle to good aviation cyber-physical system (ACPS) design, which is due to a lack of an adequate scientific theoretical foundation for the subject. The absence of a good understanding of the science of aviation system convergence is not due to neglect, but rather due to its difficulty. Most complex aviation system builders have abandoned any science or engineering discipline for system convergence they simply treat it as a management problem. Aviation System convergence is almost totally absent from software engineering and engineering curricula. Hence, system convergence is particularly challenging in ACPS where fundamentally different physical and computational design concerns intersect. In this paper, we propose an integrated approach to handle System convergence of aviation cyber physical systems based on multi-dimensions, multi-views, multi-paradigm and multiple tools. This model-integrated development approach addresses the development needs of cyber physical systems through the pervasive use of models, and physical world, cyber world can be specified and modeled together, cyber world and physical world can be converged entirely, and cyber world models and physical world model can be integrated seamlessly. The effectiveness of the approach is illustrated by means of one practical case study: specifying and modeling Aircraft Systems. In this paper, We specify and model Aviation Cyber-Physical Systems with integrating Modelica, Modelicaml and Architecture Analysis & Design Language (AADL), the physical world is modeled by Modelica and Modelicaml, the cyber part is modeled by AADL and Modelicaml.

Contingency analysis is a critical activity in the context of the power infrastructure because it provides a guide for resiliency and enables the grid to continue operating even in the case of failure. In this paper, we augment this concept by introducing SOCCA, a cyber-physical security evaluation technique to plan not only for accidental contingencies but also for malicious compromises. SOCCA presents a new unified formalism to model the cyber-physical system including interconnections among cyber and physical components. The cyber-physical contingency ranking technique employed by SOCCA assesses the potential impacts of events. Contingencies are ranked according to their impact as well as attack complexity. The results are valuable in both cyber and physical domains. From a physical perspective, SOCCA scores power system contingencies based on cyber network configuration, whereas from a cyber perspective, control network vulnerabilities are ranked according to the underlying power system topology.

In military operation or emergency response situations, very frequently a commander will need to assemble and dynamically manage Community of Interest (COI) mobile groups to achieve a critical mission assigned despite failure, disconnection or compromise of COI members. We combine the designs of COI hierarchical management for scalability and reconfigurability with COI dynamic trust management for survivability and intrusion tolerance to compose a scalable, reconfigurable, and survivable COI management protocol for managing COI mission-oriented mobile groups in heterogeneous mobile environments. A COI mobile group in this environment would consist of heterogeneous mobile entities such as communication-device-carried personnel/robots and aerial or ground vehicles operated by humans exhibiting not only quality of service (QoS) characters, e.g., competence and cooperativeness, but also social behaviors, e.g., connectivity, intimacy and honesty. A COI commander or a subtask leader must measure trust with both social and QoS cognition depending on mission task characteristics and/or trustee properties to ensure successful mission execution. In this paper, we present a dynamic hierarchical trust management protocol that can learn from past experiences and adapt to changing environment conditions, e.g., increasing misbehaving node population, evolving hostility and node density, etc. to enhance agility and maximize application performance. With trust-based misbehaving node detection as an application, we demonstrate how our proposed COI trust management protocol is resilient to node failure, disconnection and capture events, and can help maximize application performance in terms of minimizing false negatives and positives in the presence of mobile nodes exhibiting vastly distinct QoS and social behaviors.

In military operation or emergency response situations, very frequently a commander will need to assemble and dynamically manage Community of Interest (COI) mobile groups to achieve a critical mission assigned despite failure, disconnection or compromise of COI members. We combine the designs of COI hierarchical management for scalability and reconfigurability with COI dynamic trust management for survivability and intrusion tolerance to compose a scalable, reconfigurable, and survivable COI management protocol for managing COI mission-oriented mobile groups in heterogeneous mobile environments. A COI mobile group in this environment would consist of heterogeneous mobile entities such as communication-device-carried personnel/robots and aerial or ground vehicles operated by humans exhibiting not only quality of service (QoS) characters, e.g., competence and cooperativeness, but also social behaviors, e.g., connectivity, intimacy and honesty. A COI commander or a subtask leader must measure trust with both social and QoS cognition depending on mission task characteristics and/or trustee properties to ensure successful mission execution. In this paper, we present a dynamic hierarchical trust management protocol that can learn from past experiences and adapt to changing environment conditions, e.g., increasing misbehaving node population, evolving hostility and node density, etc. to enhance agility and maximize application performance. With trust-based misbehaving node detection as an application, we demonstrate how our proposed COI trust management protocol is resilient to node failure, disconnection and capture events, and can help maximize application performance in terms of minimizing false negatives and positives in the presence of mobile nodes exhibiting vastly distinct QoS and social behaviors.

The shrew distributed denial of service (DDoS) attack is very detrimental for many applications, since it can throttle TCP flows to a small fraction of their ideal rate at very low attack cost. Earlier works mainly focused on empirical studies of defending against the shrew DDoS, and very few of them provided analytic results about the attack itself. In this paper, we propose a mathematical model for estimating attack effect of this stealthy type of DDoS. By originally capturing the adjustment behaviors of victim TCPs congestion window, our model can comprehensively evaluate the combined impact of attack pattern (i.e., how the attack is configured) and network environment on attack effect (the existing models failed to consider the impact of network environment). Henceforth, our model has higher accuracy over a wider range of network environments. The relative error of our model remains around 10% for most attack patterns and network environments, whereas the relative error of the benchmark model in previous works has a mean value of 69.57%, and it could be more than 180% in some cases. More importantly, our model reveals some novel properties of the shrew attack from the interaction between attack pattern and network environment, such as the minimum cost formula to launch a successful attack, and the maximum effect formula of a shrew attack. With them, we are able to find out how to adaptively tune the attack parameters (e.g., the DoS burst length) to improve its attack effect in a given network environment, and how to reconfigure the network resource (e.g., the bottleneck buffer size) to mitigate the shrew DDoS with a given attack pattern. Finally, based on our theoretical results, we put forward a simple strategy to defend the shrew attack. The simulation results indicate that this strategy can remarkably increase TCP throughput by nearly half of the bottleneck bandwidth (and can be higher) for general attack patterns.

Distributed Denial of Service (DDoS) attacks are one of the most important threads in network systems. Due to the distributed nature, DDoS attacks are very hard to detect, while they also have the destructive potential of classical denial of service attacks. In this study, a novel 2-step system is proposed for the detection of DDoS attacks. In the first step an anomaly detection is performed on the destination IP traffic. If an anomaly is detected on the network, the system proceeds into the second step where a decision on every user is made due to the behaviour models. Hence, it is possible to detect attacks in the network that diverges from users' behavior model.

This paper presents one-layer projection neural networks based on projection operators for solving constrained variational inequalities and related optimization problems. Sufficient conditions for global convergence of the proposed neural networks are provided based on Lyapunov stability. Compared with the existing neural networks for variational inequalities and optimization, the proposed neural networks have lower model complexities. In addition, some improved criteria for global convergence are given. Compared with our previous work, a design parameter has been added in the projection neural network models, and it results in some improved performance. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural networks.

By exploiting the communication infrastructure among the sensors, actuators, and control systems, attackers may compromise the security of smart-grid systems, with techniques such as denial-of-service (DoS) attack, random attack, and data-injection attack. In this paper, we present a mathematical model of the system to study these pitfalls and propose a robust security framework for the smart grid. Our framework adopts the Kalman filter to estimate the variables of a wide range of state processes in the model. The estimates from the Kalman filter and the system readings are then fed into the χ2-detector or the proposed Euclidean detector. The χ2-detector is a proven effective exploratory method used with the Kalman filter for the measurement of the relationship between dependent variables and a series of predictor variables. The χ2-detector can detect system faults/attacks, such as DoS attack, short-term, and long-term random attacks. However, the studies show that the χ2-detector is unable to detect the statistically derived false data-injection attack. To overcome this limitation, we prove that the Euclidean detector can effectively detect such a sophisticated injection attack.

The security of Smart Grid, being one of the very important aspects of the Smart Grid system, is studied in this paper. We first discuss different pitfalls in the security of the Smart Grid system considering the communication infrastructure among the sensors, actuators, and control systems. Following that, we derive a mathematical model of the system and propose a robust security framework for power grid. To effectively estimate the variables of a wide range of state processes in the model, we adopt Kalman Filter in the framework. The Kalman Filter estimates and system readings are then fed into the χ2-square detectors and the proposed Euclidean detectors, which can detect various attacks and faults in the power system including False Data Injection Attacks. The χ2-detector is a proven-effective exploratory method used with Kalman Filter for the measurement of the relationship between dependent variables and a series of predictor variables. The χ2-detector can detect system faults/attacks such as replay and DoS attacks. However, the study shows that the χ2-detector detectors are unable to detect statistically derived False Data Injection Attacks while the Euclidean distance metrics can identify such sophisticated injection attacks.