Data Mining Practical Machine Learning Tools and Techniques

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

In this paper, we give for constant $k$ a linear-time algorithm that, given a graph $G=(V,E)$, determines whether the treewidth of $G$ is at most $k$ and, if so, finds a tree-decomposition of $G$ with treewidth at most $k$. A consequence is that every minor-closed class of graphs that does not contain all planar graphs has a linear-time recognition algorithm. Another consequence is that a similar result holds when we look instead for path-decompositions with pathwidth at most some constant $k$.

/pdf/a-linear-time-algorithm-for-finding-tree-decompositions-of-4u8h6zpm0r.pdf

A Linear-Time Algorithm for Finding Tree-Decompositions of Small Treewidth

A partial k -arboretum of graphs with bounded treewidth

Hierarchical decompositions of graphs are interesting for algorithmic purposes There are several types of hierarchical decompositions Tree decompositions are the best known ones On graphs of tree-width at most k , ie, that have tree decompositions of width at most k , where k is fixed, every decision or optimization problem expressible in monadic second-order logic has a linear algorithm We prove that this is also the case for graphs of clique-width at most k , where this complexity measure is associated with hierarchical decompositions of another type, and where logical formulas are no longer allowed to use edge set quantifications We develop applications to several classes of graphs that include cographs and are, like cographs, defined by forbidding subgraphs with ``too many'' induced paths with four vertices

/pdf/linear-time-solvable-optimization-problems-on-graphs-of-5co93faxql.pdf

Linear Time Solvable Optimization Problems on Graphs of Bounded Clique-Width

Pervasive growth of Internet of Things (IoT) is visible across the globe. The 2016 Dyn cyberattack exposed the critical fault-lines among smart networks. Security of IoT has become a critical concern. The danger exposed by infested Internet-connected Things not only affects the security of IoT but also threatens the complete Internet eco-system which can possibly exploit the vulnerable Things (smart devices) deployed as botnets. Mirai malware compromised the video surveillance devices and paralyzed Internet via distributed denial of service attacks. In the recent past, security attack vectors have evolved bothways, in terms of complexity and diversity. Hence, to identify and prevent or detect novel attacks, it is important to analyze techniques in IoT context. This survey classifies the IoT security threats and challenges for IoT networks by evaluating existing defense techniques. Our main focus is on network intrusion detection systems (NIDSs); hence, this paper reviews existing NIDS implementation tools and datasets as well as free and open-source network sniffing software. Then, it surveys, analyzes, and compares state-of-the-art NIDS proposals in the IoT context in terms of architecture, detection methodologies, validation strategies, treated threats, and algorithm deployments. The review deals with both traditional and machine learning (ML) NIDS techniques and discusses future directions. In this survey, our focus is on IoT NIDS deployed via ML since learning algorithms have a good success rate in security and privacy. The survey provides a comprehensive review of NIDSs deploying different aspects of learning techniques for IoT, unlike other top surveys targeting the traditional systems. We believe that, this paper will be useful for academia and industry research, first, to identify IoT threats and challenges, second, to implement their own NIDS and finally to propose new smart techniques in IoT context considering IoT limitations. Moreover, the survey will enable security individuals differentiate IoT NIDS from traditional ones.

Network Intrusion Detection for IoT Security Based on Learning Techniques

Monadic second-order evaluations on tree-decomposable graphs

Network Function Virtualization (NFV) is a promising technology that is receiving significant attention in both academia and the industry. NFV paradigm proposes to decouple Network Functions (NFs) from dedicated hardware equipment, offering a better sharing of physical resources and providing more flexibility to network operators. However, in such environment, efficient management mechanisms are crucial to address the problem of Placement and Chaining of Virtual Network Functions (PC-VNF). In this paper, we introduce a PC-VNF model based on a flexible resource allocation approach that takes into account service requirements in terms of latency, in addition to traditional connectivity and resource utilization. This is particularly important for emerging 5G services such as ultrareliable, low latency and massive machine type communications. The end-to-end performance needs to meet the user expectations as well as service requirements to provide the desired QoS/QoE. Our main goal is to determine the optimal VNF placement minimizing resource consumption while providing specific latency (i.e., end-to-end delay) and avoiding violation of Service Level Agreements (SLA) by constraining allocated resources to a given VNF to reach its required performance. Results show that our approach achieves the required latency with better resources utilization compared to the classical approaches, with a reduction of up to 40% of resource consumption and a higher rate of accepted requests by recovering 15 to 60 % of the rejected requests.

Delay-aware VNF placement and chaining based on a flexible resource allocation approach

Every graph generated by a hyperedge replacement graph-grammar can be represented by a tree, namely the derivation tree of the derivation sequence that produced it. Certain functions on graphs can be computed recursively on the derivation trees of these graphs. By using monadic second-order logic and semiring homomorphisms, we describe in a single formalism a large class of such functions. Polynomial and even linear algorithms can be constructed for some of these functions. We unify similar results obtained by Takamizawa et al. (1982), Bern et al. (1987), Arnborg et al. (1991) and Habel et al. (1989).

/pdf/monadic-second-order-evaluations-on-tree-decomposable-graphs-3osgkhojih.pdf

Monadic Second-Order Evaluations on Tree-Decomposable Graphs

We use Schnyder woods of 3-connected planar graphs to produce convex straight-line drawings on a grid of size $(n-2-\Delta)\times (n-2-\Delta).$ The parameter $\Delta\geq 0$ depends on the Schnyder wood used for the drawing. This parameter is in the range $0 \leq \Delta\leq {n}/{2}-2.$ The algorithm is a refinement of the face-counting algorithm; thus, in particular, the size of the grid is at most $(f-2)\times(f-2).$ The above bound on the grid size simultaneously matches or improves all previously known bounds for convex drawings, in particular Schnyder's and the recent Zhang and He bound for triangulations and the Chrobak and Kant bound for 3-connected planar graphs. The algorithm takes linear time. The drawing algorithm has been implemented and tested. The expected grid size for the drawing of a random triangulation is close to $\frac{7}{8}n\times\frac{7}{8}n.$ For a random 3-connected plane graph, tests show that the expected size of the drawing is $\frac{3}{4}n\times\frac{3}{4}n.$

/pdf/convex-drawings-of-3-connected-plane-graphs-23d0idmsqj.pdf

Mohamed Mosbah

Papers

Network Intrusion Detection for IoT Security Based on Learning Techniques

Monadic second-order evaluations on tree-decomposable graphs

Delay-aware VNF placement and chaining based on a flexible resource allocation approach

Monadic Second-Order Evaluations on Tree-Decomposable Graphs

Convex Drawings of 3-Connected Plane Graphs