Threat analysis of IoT networks using artificial neural network intrusion detection system

The Internet of things (IoT) is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However, as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using internet packet traces, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.

Requirement Risk Level Forecast Using Bayesian Networks Classifiers

Requirement engineering is a key issue in the development of a software project. Like any other development activity it is not without risks. This work is about the empirical study of risks of requirements by applying machine learning techniques, specifically Bayesian networks classifiers. We have defined several models to predict the risk level for a given requirement using three dataset that collect metrics taken from the requirement specifications of different projects. The classification accuracy of the Bayesian models obtained is evaluated and compared using several classification performance measures. The results of the experiments show that the Bayesians networks allow obtaining valid predictors. Specifically, a tree augmented network structure shows a competitive experimental performance in all datasets. Besides, the relations established between the variables collected to determine the level of risk in a requirement, match with those set by requirement engineers. We show that Bayesian networks are valid tools for the automation of risks assessment in requirement engineering.

Preventing encrypted traffic analysis

Many existing encrypted Internet protocols leak information through packet sizes and timing. Though seemingly innocuous, prior work has shown that such leakage can be used to recover part or all of the plaintext being encrypted. The prevalence of encrypted protocols as the underpinning of such critical services as e-commerce, remote login, and anonymity networks and the increasing feasibility of attacks on these services represent a considerable risk to communications security. Existing mechanisms for preventing traffic analysis focus on re-routing and padding. These prevention techniques have considerable resource and overhead requirements. Furthermore, padding is easily detectable and, in some cases, can introduce its own vulnerabilities. To address these shortcomings, we propose embedding real traffic in synthetically generated encrypted cover traffic. Novel to our approach is our use of realistic network protocol behavior models to generate cover traffic. The observable traffic we generate also has the benefit of being indistinguishable from other real encrypted traffic further thwarting an adversary's ability to target attacks. In this dissertation, we introduce the design of a proxy system called TrafficMimic that implements realistic cover traffic tunneling and can be used alone or integrated with the Tor anonymity system. We describe the cover traffic generation process including the subtleties of implementing a secure traffic generator. We show that TrafficMimic cover traffic can fool a complex protocol classification attack with 91% of the accuracy of real traffic. TrafficMimic cover traffic is also not detected by a binary classification attack specifically designed to detect TrafficMimic. We evaluate the performance of tunneling with independent cover traffic models and find that they are comparable, and, in some cases, more efficient than generic constant-rate defenses. We then use simulation and analytic modeling to understand the performance of cover traffic tunneling more deeply. We find that we can take measurements from real or simulated traffic with no tunneling and use them to estimate parameters for an accurate analytic model of the performance impact of cover traffic tunneling. Once validated, we use this model to better understand how delay, bandwidth, tunnel slowdown, and stability affect cover traffic tunneling. Finally, we take the insights from our simulation study and develop several biasing techniques that we can use to match the cover traffic to the real traffic while simultaneously bounding external information leakage. We study these bias methods using simulation and evaluate their security using a Bayesian inference attack. We find that we can safely improve performance with biasing while preventing both traffic analysis and defense detection attacks. We then apply these biasing methods to the real TrafficMimic implementation and evaluate it on the Internet. We find that biasing can provide 3-5x improvement in bandwidth for bulk transfers and 2.5-9.5x speedup for Web browsing over tunneling without biasing.

Data surveillance for infectious diseases: models, complex networks and machine learning

In this thesis, we investigate the role of applied physics in epidemiological surveillance through the application of mathematical models, network science and machine learning. The spread of a communicable disease depends on many biological, social, and health factors. The large masses of data available make it possible, on the one hand, to monitor the evolution and spread of pathogenic organisms; on the other hand, to study the behavior of people, their opinions and habits. Presented here are three lines of research in which an attempt was made to solve real epidemiological problems through data analysis and the use of statistical and mathematical models. In Chapter 1, we applied language-inspired Deep Learning models to transform influenza protein sequences into vectors encoding their information content. We then attempted to reconstruct the antigenic properties of different viral strains using regression models and to identify the mutations responsible for vaccine escape. In Chapter 2, we constructed a compartmental model to describe the spread of a bacterium within a hospital ward. The model was informed and validated on time series of clinical measurements, and a sensitivity analysis was used to assess the impact of different control measures. Finally (Chapter 3) we reconstructed the network of retweets among COVID-19 themed Twitter users in the early months of the SARS-CoV-2 pandemic. By means of community detection algorithms and centrality measures, we characterized users’ attention shifts in the network, showing that scientific communities, initially the most retweeted, lost influence over time to national political communities. In the Conclusion, we highlighted the importance of the work done in light of the main contemporary challenges for epidemiological surveillance. In particular, we present reflections on the importance of nowcasting and forecasting, the relationship between data and scientific research, and the need to unite the different scales of epidemiological surveillance.

PARTITIONED ANALYSIS FOR DIMENSIONALLY-HETEROGENEOUS HYDRAULIC NETWORKS

In this work an iterative strategy is developed to tackle the problem of coupling dimensionally-heterogeneous models in the context of fluid mechanics. The procedure proposed here makes use of a reinterpretation of the original problem as a nonlinear interface problem for which classical nonlinear solvers can be applied. Strong coupling of the partitions is achieved while dealing with different codes for each partition, each code in black-box mode. The main application for which this procedure is envisaged arises when modeling hydraulic networks in which complex and simple subsystems are treated using detailed and simplified models, correspondingly. The potentialities and the performance of the strategy are assessed through several examples involving transient flows and complex network configurations.

Communication structure of cortical networks

Large-scale cortical networks exhibit characteristic topological properties that shape communication between brain regions and global cortical dynamics. Analysis of complex networks allows the description of connectedness, distance, clustering, and centrality that reveal different aspects of how the network's nodes communicate. Here, we focus on a novel analysis of complex walks in a series of mammalian cortical networks that model potential dynamics of information flow between individual brain regions. We introduce two new measures called absorption and driftness. Absorption is the average length of random walks between any two nodes, and takes into account all paths that may diffuse activity throughout the network. Driftness is the ratio between absorption and the corresponding shortest path length. For a given node of the network, we also define four related measurements, namely in-and out-absorption as well as in-and out-driftness, as the averages of the corresponding measures from all nodes to that node, and from that node to all nodes, respectively. We find that the cat thalamo-cortical system incorporates features of two classic network topologies, Erdos-Renyi graphs with respect to in-absorption and in-driftness, and configuration models with respect to out-absorption and out-driftness. Moreover, taken together these four measures separate the network nodes based on broad functional roles (visual, auditory, somatomotor, and frontolimbic).

Gene Expression Complex Networks: Synthesis, Identification, and Analysis

Thanks to recent advances in molecular biology, allied to an ever increasing amount of experimental data, the functional state of thousands of genes can now be extracted simultaneously by using methods such as cDNA microarrays and RNA-Seq. Particularly important related investigations are the modeling and identification of gene regulatory networks from expression data sets. Such a knowledge is fundamental for many applications, such as disease treatment, therapeutic intervention strategies and drugs design, as well as for planning high-throughput new experiments. Methods have been developed for gene networks modeling and identification from expression profiles. However, an important open problem regards how to validate such approaches and its results. This work presents an objective approach for validation of gene network modeling and identification which comprises the following three main aspects: (1) Artificial Gene Networks (AGNs) model generation through theoretical models of complex networks, which is used to simulate temporal expression data; (2) a computational method for gene network identification from the simulated data, which is founded on a feature selection approach where a target gene is fixed and the expression profile is observed for all other genes in order to identify a relevant subset of predictors; and (3) validation of the identified AGN-based network through comparison with the original network. The proposed framework allows several types of AGNs to be generated and used in order to simulate temporal expression data. The results of the network identification method can then be compared to the original network in order to estimate its properties and accuracy. Some of the most important theoretical models of complex networks have been assessed: the uniformly-random Erdos-Renyi (ER), the small-world Watts-Strogatz (WS), the scale-free Barabasi-Albert (BA), and geographical networks (GG). The experimental results indicate that the inference method was sensitive to average degree k variation, decreasing its network recovery rate with the increase of k. The signal size was important for the inference method to get better accuracy in the network identification rate, presenting very good results with small expression profiles. However, the adopted inference method was not sensible to recognize distinct structures of interaction among genes, presenting a similar behavior when applied to different network topologies. In summary, the proposed framework, though simple, was adequate for the validation of the inferred networks by identifying some properties of the evaluated method, which can be extended to other inference methods.

Using Bayesian networks with rule extraction to infer the risk of weed infestation in a corn-crop

This paper describes the modeling of a weed infestation risk inference system that implements a collaborative inference scheme based on rules extracted from two Bayesian network classifiers. The first Bayesian classifier infers a categorical variable value for the weed-crop competitiveness using as input categorical variables for the total density of weeds and corresponding proportions of narrow and broad-leaved weeds. The inferred categorical variable values for the weed-crop competitiveness along with three other categorical variables extracted from estimated maps for the weed seed production and weed coverage are then used as input for a second Bayesian network classifier to infer categorical variables values for the risk of infestation. Weed biomass and yield loss data samples are used to learn the probability relationship among the nodes of the first and second Bayesian classifiers in a supervised fashion, respectively. For comparison purposes, two types of Bayesian network structures are considered, namely an expert-based Bayesian classifier and a naive Bayes classifier. The inference system focused on the knowledge interpretation by translating a Bayesian classifier into a set of classification rules. The results obtained for the risk inference in a corn-crop field are presented and discussed. (C) 2009 Elsevier Ltd. All rights reserved.

Dynamic models for computer viruses

Computer viruses are an important risk to computational systems endangering either corporations of all sizes or personal computers used for domestic applications. Here, classical epidemiological models for disease propagation are adapted to computer networks and, by using simple systems identification techniques a model called SAIC (Susceptible, Antidotal, Infectious, Contaminated) is developed. Real data about computer viruses are used to validate the model. (c) 2008 Elsevier Ltd. All rights reserved.

Risk premiums and benefit measures for generalized-expected-utility theories

Standard tools for the analysis of economic problems involving uncertainty, including risk premiums, certainty equivalents and the notions of absolute and relative risk aversion, are developed without making specific assumptions on functional form beyond the basic requirements of monotonicity, transitivity, continuity, and the presumption that individuals prefer certainty to risk. Individuals are not required to display probabilistic sophistication. The approach relies on the distance and benefit functions to characterize preferences relative to a given state-contingent vector of outcomes. The distance and benefit functions are used to derive absolute and relative risk premiums and to characterize preferences exhibiting constant absolute risk aversion (CARA) and constant relative risk aversion (CRRA). A generalization of the notion of Schur-concavity is presented. If preferences are generalized Schur concave, the absolute and relative risk premiums are generalized Schur convex, and the certainty equivalents are generalized Schur concave.

Comparing predictions of extinction risk using models and subjective judgement

Models of population dynamics are commonly used to predict risks in ecology, particularly risks of population decline. There is often considerable uncertainty associated with these predictions. However, alternatives to predictions based on population models have not been assessed. We used simulation models of hypothetical species to generate the kinds of data that might typically be available to ecologists and then invited other researchers to predict risks of population declines using these data. The accuracy of the predictions was assessed by comparison with the forecasts of the original model. The researchers used either population models or subjective judgement to make their predictions. Predictions made using models were only slightly more accurate than subjective judgements of risk. However, predictions using models tended to be unbiased, while subjective judgements were biased towards over-estimation. Psychology literature suggests that the bias of subjective judgements is likely to vary somewhat unpredictably among people, depending on their stake in the outcome. This will make subjective predictions more uncertain and less transparent than those based on models. (C) 2004 Elsevier SAS. All rights reserved.

Analysis of dynamic models for structural insight and model reduction .2. A multi-stage compressor shutdown case-study

In this second paper, the three structural measures which have been developed are used in the modelling of a three stage centrifugal synthesis gas compressor. The goal of this case study is to determine the essential mathematical structure which must be incorporated into the compressor model to accurately model the shutdown of this system. A simple, accurate and functional model of the system is created via three structural measures. It was found that the model can be correctly reduced into its basic modes and that the order of the differential system can be reduced from 51(st) to 20(th). Of the 31 differential equational 21 reduce to algebraic relations, 8 become constants and 2 can be deleted thereby increasing the algebraic set from 70 to 91 equations. An interpretation is also obtained as to which physical phenomena are dominating the dynamics of the compressor add whether the compressor will enter surge during the shutdown. Comparisons of the reduced model performance against the full model are given, showing the accuracy and applicability of the approach. Copyright (C) 1996 Elsevier Science Ltd

Type of Alcoholic Beverage and Risk of Head and Neck Cancer-025EFA Pooled Analysis Within the INHANCE Consortium

The authors pooled data from 15 case-control studies of head and neck cancer (9,107 cases, 14,219 controls) to investigate the independent associations with consumption of beer, wine, and liquor. In particular, they calculated associations with different measures of beverage consumption separately for subjects who drank beer only (858 cases, 986 controls), for liquor-only drinkers (499 cases, 527 controls), and for wine-only drinkers (1,021 cases, 2,460 controls), with alcohol never drinkers (1,124 cases, 3,487 controls) used as a common reference group. The authors observed similar associations with ethanol-standardized consumption frequency for beer-only drinkers (odds ratios (ORs) = 1.6, 1.9, 2.2, and 5.4 for <= 5, 6-15, 16-30, and > 30 drinks per week, respectively; P(trend) < 0.0001) and liquor-only drinkers (ORs = 1.6, 1.5, 2.3, and 3.6; P < 0.0001). Among wine-only drinkers, the odds ratios for moderate levels of consumption frequency approached the null, whereas those for higher consumption levels were comparable to those of drinkers of other beverage types (ORs = 1.1, 1.2, 1.9, and 6.3; P < 0.0001). Study findings suggest that the relative risks of head and neck cancer for beer and liquor are comparable. The authors observed weaker associations with moderate wine consumption, although they cannot rule out confounding from diet and other lifestyle factors as an explanation for this finding. Given the presence of heterogeneity in study-specific results, their findings should be interpreted with caution.

Genetic Analysis of Age-at-Onset for Cardiovascular Risk Factors in a Brazilian Family Study

Background/Aims: Statistical analysis of age-at-onset involving family data is particularly complicated because there is a correlation pattern that needs to be modeled and also because there are measurements that are censored. In this paper, our main purpose was to evaluate the effect of genetic and shared family environmental factors on age-at-onset of three cardiovascular risk factors: hypertension, diabetes and high cholesterol. Methods: The mixed-effects Cox model proposed by Pankratz et al. [2005] was used to analyze the data from 81 families, involving 1,675 individuals from the village of Baependi, in the state of Minas Gerais, Brazil. Results: The analyses performed showed that the polygenic effect plays a greater role than the shared family environmental effect in explaining the variability of the age-at-onset of hypertension, diabetes and high cholesterol. The model which simultaneously evaluated both effects indicated that there are individuals which may have risk of hypertension due to polygenic effects 130% higher than the overall average risk for the entire sample. For diabetes and high cholesterol the risks of some individuals were 115 and 45%, respectively, higher than the overall average risk for the entire population. Conclusions: Results showed evidence of significant polygenic effects indicating that age-at-onset is a useful trait for gene mapping of the common complex diseases analyzed. In addition, we found that the polygenic random component might absorb the effects of some covariates usually considered in the risk evaluation, such as gender, age and BMI. Copyright (C) 2008 S. Karger AG, Basel

Comparative analysis between statistical and artificial intelligence models in business failure prediction

A growing number of predicting corporate failure models has emerged since 60s. Economic and social consequences of business failure can be dramatic, thus it is not surprise that the issue has been of growing interest in academic research as well as in business context. The main purpose of this study is to compare the predictive ability of five developed models based on three statistical techniques (Discriminant Analysis, Logit and Probit) and two models based on Artificial Intelligence (Neural Networks and Rough Sets). The five models were employed to a dataset of 420 non-bankrupt firms and 125 bankrupt firms belonging to the textile and clothing industry, over the period 2003–09. Results show that all the models performed well, with an overall correct classification level higher than 90%, and a type II error always less than 2%. The type I error increases as we move away from the year prior to failure. Our models contribute to the discussion of corporate financial distress causes. Moreover it can be used to assist decisions of creditors, investors and auditors. Additionally, this research can be of great contribution to devisers of national economic policies that aim to reduce industrial unemployment.