Search

Multiple attacks have shown that in-vehicle networks have vulnerabilities which can be exploited. Securing the Controller Area Network (CAN) for modern vehicles has become a necessary task for car manufacturers. Some attacks inject potentially large amount of fake messages into the CAN network; however, such attacks are relatively easy to detect. In more sophisticated attacks, the original messages are modified, making the detection a more complex problem. In this paper, we present a novel machine learning based intrusion detection method for CAN networks. We focus on detecting message modification attacks, which do not change the timing patterns of communications. Our proposed temporal convolutional network-based solution can learn the normal behavior of CAN signals and differentiate them from malicious ones. The method is evaluated on multiple CAN-bus message IDs from two public datasets including different types of attacks. Performance results show that our lightweight approach compares favorably to the state-of-the-art unsupervised learning approach, achieving similar or better accuracy for a wide range of scenarios with a significantly lower false positive rate.

In this paper, we introduce a novel approach to optimizing the control of systems that can be modeled as Markov decision processes (MDPs) with a threshold-based optimal policy. Our method is based on a specific type of genetic program known as symbolic regression (SR). We present how the performance of this program can be greatly improved by taking into account the corresponding MDP framework in which we apply it. The proposed method has two main advantages: (1) it results in near-optimal decision policies, and (2) in contrast to other algorithms, it generates closed-form approximations. Obtaining an explicit expression for the decision policy gives the opportunity to conduct sensitivity analysis, and allows instant calculation of a new threshold function for any change in the parameters. We emphasize that the introduced technique is highly general and applicable to MDPs that have a threshold-based policy. Extensive experimentation demonstrates the usefulness of the method.

Various systems across a broad range of applications contain tandem queues. Strong dependence between the servers has proven to make such networks complicated and difficult to study. Exact analysis is rarely computationally tractable and sometimes not even possible. Nevertheless, as it is most often the case in reality, there are costs associated with running such systems, and therefore, optimizing the control of tandem queues is of main interest from both a theoretical and a practical point of view. Motivated by this, the present paper considers a tandem queueing network with linear holding costs and a startup cost for the second server. In our work, we present a rather intuitive, easy to understand, and at the same time very accurate technique to approximate the optimal decision policy. Extensive numerical experimentation shows that the approximation works extremely well for a wide range of parameter combinations.

In this study we identify spatial regions based on an empirical data set consisting of time-dependent origin-destination (OD) pairs. This OD data consists of electronic traces collected from smart phone data by Google in the Amsterdam metropolitan region and is aggregated by the volume of trips per hour at neighborhood level. In this study we cluster the pairs by space and time to gain insight in both aspects regarding travel characteristics. We show that spatially connected clusters appear when we use a performance metric called modularity on the OD data when directionality is incorporated.

Various types of systems across a broad range of disciplines contain tandem queues with nested sessions. Strong dependence between the servers has proved to make such networks complicated and difficult to study. Exact analysis is in most of the cases intractable. Moreover, even when performance metrics such as the saturation throughput and the utilization rates of the servers are known, determining the limiting factor of such a network can be far from trivial. In our work, we present a simple, tractable and nevertheless relatively accurate method for approximating the above mentioned performance measurements for any server in a given network. In addition, we propose an extension to the intuitive “slowest server rule” for identification of the bottleneck, and show through extensive numerical experiments that this method works very well.

In this study, we identify spatial regions based on an empirical data set consisting of time-dependent origin-destination (OD) pairs. These OD pairs consist of electronic traces collected from smartphone data by Google in the Amsterdam metropolitan region and is aggregated by the volume of trips per hour at neighbourhood level. By means of community detection, we examine the structure of this empirical data set in terms of connectedness. We show that we can distinguish spatially connected regions when we use a performance metric called modularity and the trip directionality is incorporated. From this, we proceed to analyse variations in the partitions that arise due to the non-optimal greedy optimisation method. We use a method known as ensemble learning to combine these variations by means of the overlap in community partitions. Ultimately, the combined partition leads to a more consistent result when evaluated again, compared to the individual partitions. Analysis of the partitions gives insights with respect to connectivity and spatial travel patterns, thereby supporting policy makers in their decisions for future infra structural adjustments. © 2019, The Author(s).

In service function chaining, data flows from a particular application or user travel along a pre-defined sequence of network functions. Appropriate service function chaining resource allocation is required to comply with the service level required by the application. In this paper, we introduce a dynamic priority assignment for flows that compete for service using a particular network function in a chain. Using the recent results of the performance metrics of transient birth-death processes, we analyse this priority assignment and develop an optimal strategy for selecting a (cheap) low-or (expensive) high-priority service, given the flow's service level agreement requirements. A decision table can, thus, be created to facilitate the fast, online priority scheduling of newly arriving flows requesting service. © 2019 IEEE.

The chapter summarizes activities of COST IC1304 ACROSS European Project corresponding to traffic management for Cloud Federation (CF). In particular, we provide a survey of CF architectures and standardization activities. We present comprehensive multi-level model for traffic management in CF that consists of five levels: Level 5 - Strategies for building CF, Level 4 - Network for CF, Level 3 - Service specification and provision, Level 2 - Service composition and orchestration, and Level 1 - Task service in cloud resources. For each level we propose specific methods and algorithms. The effectiveness of these solutions were verified by simulation and analytical methods. Finally, we also describe specialized simulator for testing CF solution in IoT environment.

Pre-congestion notification (PCN) protects inelastic traffic by using feedback on network link loads on and acting upon this accordingly. These actions comprise to admission control and termination of flows. Two PCN architectures have been defined by IETF: the centralized and decentralized PCN architecture. The decentralized PCN architecture has received much attention in the literature whereas the centralized PCN architecture has not. In the decentralized architecture, feedback is sent from the egress nodes to ingress nodes, which then take and apply decisions regarding admission of new flows and/or termination of ongoing flows. Signaling occurs only between ingress and egress nodes. In the centralized architecture these decisions are made at a central node, which requires proper signaling for action and information exchange between the central node and the egress and ingress nodes. This signaling has been suggested by other authors, but is not fully defined yet. Our contribution is twofold. We define signaling in the centralized PCN architecture focussing on flow termination, which completes the definition of the signaling in the centralized PCN architecture. Secondly, we run extensive simulations showing that the proposed signaling works well and that the performances of the centralized PCN and the decentralized PCN architectures are similar. Hence, it is expected that results from existing research on the effectiveness of decentralized PCN are also valid when the centralized PCN architecture is used. © 2017 Elsevier B.V.

The advent of renewable energy sources has huge implications for the design and control of power grids. On the engineering side, reliability is currently ensured by strict con- straints on current, voltage and temperature. However, with growing supply-side uncertainty induced by renewables, these will need to be replaced by probabilistic guarantees, allowing constraints on a given line to be violated with a low probability, e.g., several minutes per year. In the present note we illustrate, using large deviations techniques, how replacing (probabilistic) current constraints by temperature constraints can lead to capacity gains in power grids.

Various canonical forms of general resource allocation problemsarise naturally across a broad spectrum of computer systems andcommunication networks. As the complexities of these systemsand networks continue to grow, together with ubiquitous advancesin technology, new approaches and methods are required to effec-tively and efficiently solve these problems. Such environments of-ten consist of different types of resources that are allocated in com-bination to serve demand whose behavior over time is characterizedby different types of uncertainty and variability. Each type of re-source has a different reward and cost structure that ranges from thebest of a set of primary resource allocation options, having the high-est reward, highest cost and highest net-benefit, to a secondary re-source allocation option, having the lowest reward, lowest cost andlowest net-benefit. Each type of resource also has different struc-tures for the flexibility and cost of making changes to the allocationcapacity. The resource management optimization problem we con-sider consists of adaptively determining the primary and secondaryresource allocation capacities that serve the uncertain demand andthat maximize the expected net-benefit over a time horizon of in-terest based on the foregoing reward, cost and flexibility structuralproperties of the different types of resources.The general class of resource allocation problems studied in thispaper arises in a wide variety of application domains such as cloudcomputing and data center environments, computer and communi-cation networks, and energy-aware and smart power grid environ-ments, among many others. Across these and many other domain-specific resource allocation problems, there is a common need forthe dynamic adjustment of allocations among multiple types of re-sources, each with different structural properties, to satisfy time-varying and uncertain demand. Taking a financial mathematicsapproach that hedges against future risks associated with resourceallocation decisions and uncertain demand, we consider the under-lying fundamental stochastic optimal control problem where thedynamic control policy that allocates primary resource capacitiesto serve uncertain demand is a variational stochastic process withconditions on its derivative, which in turn determines the secondaryresource allocation capacity. The objective is to maximize the ex-pected discounted net-benefit over time based on the structural prop

Osteopontin (OPN) is a glycophosphoprotein with multiple intracellular and extracellular functions. In vitro, OPN enhances migration of mouse neutrophils and macrophages. In cancer, extracellular OPN facilitates migration of cancer cells via its RGD sequence. The present study was designed to investigate whether osteopontin is responsible for neutrophil and macrophage infiltration in human cancer and in particular in glioblastoma. We found that in vitro mouse neutrophil migration was RGD-dependent. In silico, we found that the OPN gene was one of the 5% most highly expressed genes in 20 out of 35 cancer microarray data sets in comparison with normal tissue in at least 30% of cancer patients. In some types of cancer, such as ovarian cancer, lung cancer and melanoma, the OPN gene was one of those with the highest expression levels in at least 90% of cancer patients. In glioblastoma, the most invasive type of brain tumours/glioma, but not in lower grades of glioma it was one of the 5% highest expressed genes in 90% of patients. In situ, we found increased protein levels of OPN in human glioblastoma versus normal human brain confirming in silico results. OPN protein expression was co-localized with neutrophils and macrophages. In conclusion, OPN in tumours not only induces migration of cancer cells but also of leucocytes.

Service orchestration has become the predominant paradigm that enables businesses to combine and integrate services offered by third parties. For the commercial viability of orchestrated services, it is crucial that they are offered at sharp price-quality ratios. A complicating factor is that many attractive third-party services often show highly variable service quality. This raises the need for mechanisms that promptly adapt the orchestration to changes in the quality delivered by third party services. In this paper, we propose a real-time QoS control mechanism that dynamically optimizes service orchestration in real time by learning and adapting to changes in third party service response time behaviors. Our approach combines the power of learning and adaptation with the power of dynamic programming. The results show that real-time service re-compositions lead to dramatic savings of cost, while meeting the service quality requirements of the end-users. The challenge here is to respond to significant response-time changes in a timely manner, while not wasting CPU cycles on unnecessary orchestration updates. Experimental results performed in a test-lab environment demonstrate that a few orchestration updates are sufficient to achieve this. © 2015 IEEE.

Surrounded by a multitude of wireless networks, users can nowadays experience significant performance improvements when smartly combining multiple networks concurrently (e.g., for transferring files). This phenomenon is called Concurrent Access (CA). Some users, which are referred to as foreground (FG) users, are able to access and utilize multiple networks simulateneously. The traffic streams from the FG users are optimized over multiple networks, in the presence of background (BG) users that can use only one network. In the literature a variety of traffic splitting algorithms have been proposed, with a focus on improving the performance of the FG users, whereas the influence of smart traffic splitting on the performance experienced by the BG users, as well as the resulting splitting ratios over the different networks, have received hardly attention. In this paper, we evaluate and compare the performance of these algorithms with respect to three quality metrics: (1) the file transfer performance of the FG traffic, (2) the file transfer performance of the BG traffic, and (3) the traffic splitting ratios, i.e. the fractions of traffic that is sent over each of the access networks. Our simulations based results provide a number of valuable insights in the pros and cons of the different job splitting and assignment algorithms.

The concurrent use of networks provides a powerful means to boost performance in areas covered by multiple networks where only limited bandwidth is available. However, despite its enormous potential for performance improvement only little is known about how to effectively exploit the potential for performance improvement in practical deployments. This raises the need for traffic-splitting-and-reassembly algorithms that are effective, yet simple and easy-to-deploy. Motivated by this, we first propose a simple analytic flow-level model, called the Concurrent Access Network (CAN) model, that optimally splits traffic in the idealized situation where there is full state information at infinitely fine-grained time granularity, leading to zero synchronization delay during the reassembly phase. Next, we present a new splitting algorithm for TCP-based networks that uses a simple score function to make on-the-fly decisions on the routing of individual TCP segments, based on the measured per-connection RTT, transmission-buffer content and throughput. Then, we use the CAN-model as a benchmark to evaluate the effectiveness and practical usefulness of the score-function based algorithm on real TCP networks in a test-lab environment. Extensive lab experimentation demonstrates that this score-function based splitting of TCP traffic is extremely efficient, leads to close-to-optimal response-time performance and is easily deployable.

We consider a general class of dynamic resource allocation problems within a stochastic optimal control framework. This class of problems arises in a wide variety of applications, each of which intrinsically involves resources of different types and demand with uncertainty and/or variability. The goal is to dynamically allocate capacity for every resource type in order to serve the uncertain/ variable demand and maximize the expected net-benefit over a time horizon of interest based on the rewards and costs associated with the different resources. We derive the optimal control policy within a singular control setting, which includes easily implementable algorithms for governing the dynamic adjustments to resource allocation capacities over time. Numerical experiments investigate various issues of both theoretical and practical interest, quantifying the significant benefits of our approach over alternative optimization approaches.

Contemporary wireless networks are based on a wide range of different technologies providing overlapping coverage. This offers users a seamless integration of connectivity by allowing to switch between networks, and opens up a promising area for boosting the performance of wireless networks. Motivated by this, we consider a networking environment in which users are able to select between the available wireless networks to minimize the mean processing times for file downloads in the presence of background traffic. The information available to the user is only the total number of jobs in each network, rather than the per-network numbers of foreground and background jobs. This leads to a complex partial information decision problem which is the focus of this paper. We develop and evaluate a Bayesian learning algorithm that optimally splits a stream of jobs that minimizes the expected sojourn time. The algorithm learns as the system operates and provides information at each decision and departure epoch. We evaluate the optimality of the partial information algorithm by comparing the performance of the algorithm with the "ideal" performance obtained by solving a Markov decision problem with full state information. To this end, we have conducted extensive experiments both numerically and in a simulation testbed with the full wireless protocol stack. The results show that the Bayesian algorithm has close to optimal performance over a wide range of parameter values. © 2011 Elsevier B.V. All rights reserved.

In this paper we investigate sequential decision mechanisms for composite web services. After executing each sub-service within a sequential workflow, decisions are made whether to terminate or continue the execution of the workflow. These decisions are based on observed response times, expected rewards, and typical Service Level Agreement parameters such as costs, penalties, and agreed response–time objectives. We propose a model for the sequential decision–making process within which we explore a couple of decision algorithms. We benchmarked these algorithms against the profit made when executing the workflow without decision–making. We show that algorithm based on backward recursion principle of dynamic programming is optimal with respect to profit. Next, we analyse the structure of erroneous decisions for both algorithms and show that significant profit gains can be obtained by sequential decision making.

The somatic IDH1R132 mutation in the isocitrate dehydrogenase 1 gene occurs in high frequency in glioma and in lower frequency in acute myeloid leukemia and thyroid cancer but not in other types of cancer. The mutation causes reduced NADPH production capacity in glioblastoma by 40% and is associated with prolonged patient survival. NADPH is a major reducing compound in cells that is essential for detoxification and may be involved in resistance of glioblastoma to treatment. IDH has never been considered important in NADPH production. Therefore, the authors investigated NADPH-producing dehydrogenases using in silico analysis of human cancer gene expression microarray data sets and metabolic mapping of human and rodent tissues to determine the role of IDH in total NADPH production. Expression of most NADPH-producing dehydrogenase genes was not elevated in 34 cancer data sets except for IDH1 in glioma and thyroid cancer, indicating an association with the IDH1 mutation. IDH activity was the main provider of NADPH in human normal brain and glioblastoma, but its role was modest in NADPH production in rodent brain and other tissues. It is concluded that rodents are a poor model to study consequences of the IDH1R132 mutation in glioblastoma.

With a large variety of wireless access technologies available, multi-homed devices may strongly improve the performance and reliability of communication when using multiple networks simultaneously. A key question for the practical application of multi-path strategies is the granularity at which the traffic streams should be dispersed among the available networks. This level of granularity may be expected to have a major impact on both the efficiency and complexity of practical realizations. Motivated by this, we compare two dynamic strategies that operate at different levels of granularity. The first strategy, which we call network selection, requires little operational complexity and dynamically assigns an arriving application data transfer to the network that delivers the highest expected performance. Our second strategy, which we call traffic-splitting, is of higher complexity and aims to optimally split individual data transfers among the available networks. To this end, we (1) develop quantitative models that describe the performance of both strategies, (2) determine the (near-)optimal algorithms for both strategies, and (3) validate the efficiency and practical usefulness of the algorithms via extensive network simulations and experiments in a real-life testbed environment. These experimental results show that the optimal strategies obtained from the theoretical models lead to extremely well-performing solutions in practical circumstances. Moreover, the results show that the splitting of data transfers, which is easy to embed in the network requiring no information on the number of flows in the system, leads to a much better performance compared to dynamic network selection.