Despite the access to enormous amounts of data, there is a holdback in the usage of machine learning in the Cyber Security field due to the lack of interpretability of ”Black­box” models and due to heterogenerous data. This project presents a method that provide insights in the decision making process in Cyber Security classification. Hybrid Ensemble Methods (HEMs), use several weak learners trained on single data features and combines the output of these in a neural network. In this thesis HEM preforms phishing website classification with high accuracy, along with interpretability. The ensemble of predictions boosts the accuracy with 8%, giving a final prediction accuracy of 93 %, which indicates that HEM are able to reconstruct correlations between the features after the interpredability stage. HEM provides information about which weak learners trained on specific information that are valuable for the classification. No samples were disregarded despite missing features. Cross validation were made across 3 random seeds and the results showed to be steady with a variance of 0.22%. An important finding was that the methods performance did not significantly change when disregarding the worst of the weak learners, meaning that adding models trained on bad data won’t sabotage the prediction. The findings of these investigations indicates that Hybrid Ensamble methods are robust and flexible. This thesis represents an attempt to construct a smarter way of making predictions, where the usage of several forms of information can be combined, in an artificially intelligent way. / Trots tillgången till enorma mängder data finns det ett bakslag i användningen av maskininlärning inom cybersäkerhetsområdet på grund av bristen på tolkning av ”Blackbox”-modeller och på grund av heterogen data. Detta projekt presenterar en metod som ger insikt i beslutsprocessen i klassificering inom cyber säkerhet. Hybrid Ensemble Methods (HEMs), använder flera svaga maskininlärningsmodeller som är tränade på enstaka datafunktioner och kombinerar resultatet av dessa i ett neuralt nätverk. I denna rapport utför HEM klassificering av nätfiskewebbplatser med hög noggrannhet, men med vinsten av tolkningsbarhet. Sammansättandet av förutsägelser ökar noggrannheten med 8 %, vilket ger en slutgiltig prediktionsnoggrannhet på 93 %, vilket indikerar att HEM kan rekonstruera korrelationer mellan funktionerna efter tolkbarhetsstadiet. HEM ger information om vilka svaga maskininlärningsmodeller, som tränats på specifik information, som är värdefulla för klassificeringen. Inga datapunkter ignorerades trots saknade datapunkter. Korsvalidering gjordes över 3 slumpmässiga dragningar och resultaten visade sig vara stabila med en varians på 0.22 %. Ett viktigt resultat var att metodernas prestanda inte förändrades nämnvärt när man bortsåg från de sämsta av de svaga modellerna, vilket innebär att modeller tränade på dålig data inte kommer att sabotera förutsägelsen. Resultaten av dessa undersökningar indikerar att Hybrid Ensamble-metoder är robusta och flexibla. Detta projekt representerar ett försök att konstruera ett smartare sätt att göra klassifieringar, där användningen av flera former av information kan kombineras, på ett artificiellt intelligent sätt.

Security threats to cyber-physical systems are targeting institutions and infrastructure around the world, and the frequency and severity of attacks are on the rise. Healthcare manufacturing, financial services, education, government, and transportation are among the industries that are the most lucrative targets for adversaries. Hacking is not just about companies, organizations, or banks; it also includes critical infrastructure. Wireless Sensors Networks, Vehicle-to-everything communication (V2X), Dynamic Message Signs (DMS), and Traffic Signal Controllers are among major Intelligent Transportation Systems (ITS) infrastructure that has already been attacked or remain vulnerable to hacking. ITS has been deployed with a focus on increasing efficiency and safety in the face of dramatic increases in travel demand. Although many studies have been performed and many security primitives have been proposed, there are significant concerns about flawless performance in a dynamic environment. A holistic security approach, in which all infrastructure performs within the satisfactory level of security remains undiscovered. Previously, hacking of road infrastructure was a rare event, however, in recent years, field devices such as DMS are hacked with higher frequency. The primary reason that transportation assets are vulnerable to cyber-attacks is due to their location. A more dramatic scenario occurs when hackers attempt to convey tampered instructions to the public. Analyzing traveler behavior in response to the hacked messages sign on the basis of empirical data is a vital step toward operating a secure and reliable transportation system. There may be room for improvement by policymakers and program managers when considering critical infrastructure vulnerabilities. With cybersecurity issues escalating every day, road users' safety has been neglected. This dissertation overcomes these challenges and contributes to the nascent but growing literature of Intelligent Transportation System (ITS) security impact-oriented risk assessment in threefold. • First, I employ a risk-based approach to conduct a threat assessment. This threat assessment performs a qualitative vulnerability-oriented threat analysis. The objective is to scrutinize safety, security, reliability, and operation issues that are prompted by a compromised Dynamic Message Signs (DMS). • Second, I examine the impact of drivers' attitudes and behaviors on compliance, route diversion behavior, and speed change behavior, under a compromised DMS. We aim to assess the determinants that are likely to contribute to drivers' compliance with forged information. To this extent, this dissertation evaluates drivers' behavior under different unauthentic messages to assess in-depth the impact of an adversarial attack on the transportation network. • Third, I evaluate distracted driving under different scenarios to assess the in-depth impact of an adversarial attack on the transportation network. To this extent, this dissertation examines factors that are contributing to the manual, visual, and cognitive distractions when drivers encountering fabricated advisory information at a compromised DMS. The results of this dissertation support the original hypothesis and indicate that with respect to the forged information drivers tend to (1) change their planned route, (2) become involved in distracting activities, and (3) change their choice speed at the presence of a compromised DMS. The main findings of this dissertation are outlined below: 1. The DMS security vulnerabilities and predisposing conditions allow adversaries to compromise ITS functionality. The risk-based approach of this study delivers the impact-likelihood matrix, which maps the adverse impacts of the threat events onto a meaningful, visual, matrix. DMS hacking adverse impacts can be categorized mainly as high-risk and medium-risk clusters. The safety, operational (i.e., monetary losses) and behavioral impacts are associated with a high-risk cluster. While the security, reliability, efficiency, and operational (i.e., congestion) impacts are associated with the medium-risk cluster. 2. Tech friendly drivers are more likely to change their route under a compromised DMS. At the same time, while they are acquiring new information, they need to lowering their speed to respond to the higher information load. Under realistic-fabricated information, about 65% of the subjects would depart from their current route. The results indicate that females and subjects with a higher driving experience are more likely to change their route. In addition, those subjects who are more sensitive to the DMS's traffic-related messages and those who use DMS under congested traffic condition are more likely to divert. Interestingly, individuals with lower education level, Asians, those who live in urban areas, and those with trouble finding their direction in new routes are less likely to pick another route rather the one they planned for. 3. Regardless of the DMS hacking scenarios, drivers would engage in at least one of the distractive activities. Among the distractive activities, cognitive distraction has the highest impact on the distracted driving likelihood. Meaning, there is a high chance that drivers think of something other than driving, look at surrounding traffic and scenery, or talk to other passengers regarding the forged information they saw on the DMS. Drivers who rely and trust in technology, and those who check traffic condition before starting their trips tend to become distracted. In addition, the result identified that at the presence of bogus information, drivers tend to slow down or stop in order to react to the DMS. That is, they would either (1) become involved in activities through the means of their phone, (2) they would mind wander, look around, and talk to a passenger about the sign, and (3) search for extra information by means of their vehicle's radio or internet. 4. Females, black individuals, subjects with a disability, older, and those with high trust in DMS are less likely to ignore the fabricated messages. In contrary, white, those who drive long hours, and those who see driving as a tedious task are more likely to ignore the bogus messages. Drivers who comply with traffic regulations and have a good driving record are likely to slow down under the tampered messages. Furthermore, female drivers and those who live in rural areas are more likely to slow down under fabricated advisory information. Furthermore, this dissertation identifies that planning for alternative route and involvement in distractive activities cause speed variation behaviors under the compromised DMS. This dissertation is the first to investigate the adverse impact of a compromised DMS on the road users and operators. I attempt to address the current gap in the literature by assessing and evaluating the impact of ITS security vulnerabilities. Broader impacts of this study include (1) to systematically raising awareness among policy-makers and engineers, (2) motivating further simulations and real-world experiments to investigate this matter further, (3) to systematically assessing the adverse impact of a security breach on transportation reliability and safety, and drivers' behavior, and (4) providing insights for system operators and decision-makers to prioritize the risk of a compromised DMS. Additionally, the outcome can be integrated with the nationwide connected vehicle and V2X implementations and security design. / Doctor of Philosophy / Security threats are targeting institutions and infrastructure around the world, and the frequency and severity of security attacks are on the rise. Healthcare manufacturing, financial services, education, government, and transportation are among the industries that are the most lucrative targets for adversaries. Hacking is not just about companies, organizations, or banks; it also includes critical infrastructure. Intelligent Transportation Systems have been deployed with a focus on increasing efficiency and safety in the face of dramatic increases in traffic volume. Although many studies have been performed and many security primitives have been proposed, there are significant concerns about flawless performance in a dynamic environment. A holistic security approach, in which all infrastructure performs within the satisfactory level of security remains undiscovered. Previously, hacking of road infrastructure was a rare event, however, in recent years, field devices, such as dynamic message signs, are hacked with higher frequency. The primary reason that transportation assets are vulnerable to cyber-attacks is that of their location in public. A more dramatic scenario occurs when hackers attempt to convey tampered instructions to the public. Analyzing traveler behavior in response to the hacked messages sign on the basis of empirical data is a vital step toward operating a secure and reliable transportation system. This study is the first to investigate the adversarial impact of a compromised message sign on the road users and operators. I attempt to address the current gap in the literature by assessing and evaluating the impact of ITS security vulnerabilities.

Much of the confusion about the effectiveness of information security programs concerns not only how to measure, but also what to measure — an issue of equivocality. Thus, to lower uncertainty for improved decision-making, it is first essential to reduce equivocality by defining, expanding, and clarifying risk factors so that metrics, the "necessary measures," can be unambiguously applied. We formulate a system that (1) allows threats to be accurately measured and tracked, (2) enables the impacts and costs of successful threats to be determined, and (3) aids in evaluating the effectiveness and return on investment of countermeasures. We then examine the quality of controls implemented to mitigate cyber risk and study how effectively they reduce the likelihood of security incidents. Improved control quality was shown to reduce the likelihood of security incidents, yet the results indicate that investing in maximum quality is not necessarily the most efficient use of resources. The next manuscript expands the discussion of cyber risk management beyond single organizations by surveying perceptions and experiences of risk factors related to 3rd parties. To validate and these findings, we undertake in an in-depth investigation of nearly 1000 real-world data breaches occurring over a ten-year period. It provides a robust data model and rich database required by a decision support system for cyber risk in the extended enterprise. To our knowledge, it is the most comprehensive field study ever conducted on the subject. Finally, we incorporate these insights, data, and factors into a simulation model that enables us study the transfer of cyber risk across different supply chain configurations and draw important managerial implications. / Ph. D.

The power grid has changed a great deal from what has been generally viewed as a traditional power grid. The modernization of the power grid has seen an increase in the integration and incorporation of computing and communication elements, creating an interdependence of both physical and cyber assets of the power grid. The fast-increasing connectivity has transformed the grid from what used to be primarily a physical system into a Cyber- Physical System (CPS). The physical elements within a power grid are well understood by power engineers; however, the newly deployed cyber aspects are new to most researchers and operators in this field. The new computing and communications structure brings new vulnerabilities along with all the benefits it provides. Cyber security of the power grid is critical due to the potential impact it can make on the community or society that relies on the critical infrastructure. These vulnerabilities have already been exploited in the attack on the Ukrainian power grid, a highly sophisticated, multi-layered attack which caused large power outages for numerous customers. There is an urgent need to understand the cyber aspects of the modernized power grid and take the necessary precautions such that the security of the CPS can be better achieved. The power grid is dependent on two main cyber infrastructures, i.e., Supervisory Control And Data Acquisition (SCADA) and Advanced Metering Infrastructure (AMI). This thesis investigates the AMI in power grids by developing a testbed environment that can be created and used to better understand and develop security strategies to remove the vulnerabilities that exist within it. The testbed is to be used to conduct and implement security strategies, i.e., an Intrusion Detections Systems (IDS), creating an emulated environment to best resemble the environment of the AMI system. A DoS flooding attack and an IDS are implemented on the emulated testbed to show the effectiveness and validate the performance of the emulated testbed. / M.S. / The power grid is becoming more digitized and is utilizing information and communication technologies more, hence the smart grid. New systems are developed and utilized in the modernized power grid that directly relies on new communication networks. The power grid is becoming more efficient and more effective due to these developments, however, there are some considerations to be made as for the security of the power grid. An important expectation of the power grid is the reliability of power delivery to its customers. New information and communication technology integration brings rise to new cyber vulnerabilities that can inhibit the functionality of the power grid. A coordinated cyber-attack was conducted against the Ukrainian power grid in 2015 that targeted the cyber vulnerabilities of the system. The attackers made sure that the grid operators were unable to observe their system being attacked via Denial of Service attacks. Smart meters are the digitized equivalent of a traditional energy meter, it wirelessly communicates with the grid operators. An increase in deployment of these smart meters makes it such that we are more dependent on them and hence creating a new vulnerability for an attack. The smart meter integration into the power grid needs to be studied and carefully considered for the prevention of attacks. A testbed is created using devices that emulate the smart meters and a network is established between the devices. The network was attacked with a Denial of Service attack to validate the testbed performance, and an Intrusion detection method was developed and applied onto the testbed to prove that the testbed created can be used to study and develop methods to cover the vulnerabilities present.

The world has become more digitized, and children use digital devices daily as games or watching tools. As technology grows stronger, the use of cyberspace and the threat coming within cyberspace grow larger by the day. Today's technology makes children active users in the cyber community as many children do in fact, use digital devices to talk to strangers, play online games and so on. There has also been increased digitization within preschool. Therefore, this thesis aims to review the existing guidelines regarding digital devices in the education system from the Swedish National Agency of Education (SNAE). Furthermore, investigate how preschool teachers translate the existing guidelines into practice for children's security online and how teachers work with cyber security awareness. The authors’, therefore conducted an interview study to gather data from teachers and principals in preschools regarding the use of digital devices. The authors’ aim to understand how teachers and principals work together with the existing guidelines to further enhance cyber security awareness among children. Multiple teachers work with digital tools in preschools. However, teachers use digital tools as a supplement to teaching children. The discussion regarding the risks and how to be safe online is not discussed as much in preschool because of the children's age. Multiple participants agreed that a separate segment for cyber security awareness would be significant.

No description available.

The thesis is focused on the Czech act no. 181/2014 Sb., on cyber security and subsequent regulations, introduces origin and importance of act, defines the state administration´s office which identifies important information systems according to regulations, and subsequently thesis detailed analyses act and regulation on cyber security in relation to the defined state administration´s office. Keynote of this thesis is show the real application of identified obligations of the act and regulation to the defined state administration´s office, especially a design, implementation and management of organizational and technical security measures, including the evaluation of real impact on information security. To achieve the set goals author of this thesis uses the analysis of legislation, and draws own conclusions from author´s position of a security technologist who actively participated in the design security policy, and implementation and management of security tools. The benefit of this thesis is complex overview of the security employees work at defined state administration´s office, overview of the real fulfilment obligations of the act and regulation of cybernetic security, and ultimately this thesis brings ideas for further development of technical security tools. This thesis can brings benefit to other important information systems administrators as a set of processes, proposals and recommendation for their own information security management system. This thesis is structurally divided into four main parts. The first theoretical part introduces origin, importance and impact of the act on state and private organizations. The second analytical part analyses act and subsequent regulations in relation to the defined state administration´s office. The third practical part shows the real application of organizational and technical security measures. The fourth last part evaluates the real impact of measures on information security.

Approved for public release; distribution is unlimited. / Cyberespionage is a prolific threat that undermines the power projection capacity of the United States through reduced economic prowess and a narrowing of the technical advantage employed by the American military. International attempts to limit hostile cyber activity through the development of institutions, normative patterns of behavior, or assimilation of existing laws do not provide the American national security decision maker with a timely or effective solution to address these threats. Unfortunately, the stove-piped, redundant and inefficient nature of the U.S. counterintelligence community does not deliver a viable alternative to mitigating cyberespionage in an effective manner. Instituting a domestic and international micro-restructuring approach within the Department of Defense (DoD) addresses the need for increased effectiveness within an environment of fiscal responsibility. Domestic restructuring places emphasis on developing a forcing mechanism that compels the DoD counterintelligence services to develop joint approaches for combating cyberespionage by directly addressing the needs of the Combatant Commands. International restructuring places an emphasis on expanding cybersecurity cooperation to like-minded nations and specifically explores the opportunity and challenges for increased cyber cooperation with Taiwan. This approach recognizes that Taiwan and the United States are both negatively affected from hostile cyber activity derived from within the People’s Republic of China.

Today, virtually every company world-wide is connected to the Internet. This wide-spread connectivity has given rise to sophisticated, targeted, Internet-based attacks. For example, between 2012 and 2013 security researchers counted an average of about 74 targeted attacks per day. These attacks are motivated by economical, financial, or political interests and commonly referred to as “Advanced Persistent Threat (APT)” attacks. Unfortunately, many of these attacks are successful and the adversaries manage to steal important data or disrupt vital services. Victims are preferably companies from vital industries, such as banks, defense contractors, or power plants. Given that these industries are well-protected, often employing a team of security specialists, the question is: How can these attacks be so successful? Researchers have identified several properties of APT attacks which make them so efficient. First, they are adaptable. This means that they can change the way they attack and the tools they use for this purpose at any given moment in time. Second, they conceal their actions and communication by using encryption, for example. This renders many defense systems useless as they assume complete access to the actual communication content. Third, their actions are stealthy — either by keeping communication to the bare minimum or by mimicking legitimate users. This makes them “fly below the radar” of defense systems which check for anomalous communication. And finally, with the goal to increase their impact or monetisation prospects, their attacks are targeted against several companies from the same industry. Since months can pass between the first attack, its detection, and comprehensive analysis, it is often too late to deploy appropriate counter-measures at businesses peers. Instead, it is much more likely that they have already been attacked successfully. This thesis tries to answer the question whether the last property (industry-wide attacks) can be used to detect such attacks. It presents the design, implementation and evaluation of a community-based intrusion detection system, capable of protecting businesses at industry-scale. The contributions of this thesis are as follows. First, it presents a novel algorithm for community detection which can detect an industry (e.g., energy, financial, or defense industries) in Internet communication. Second, it demonstrates the design, implementation, and evaluation of a distributed graph mining engine that is able to scale with the throughput of the input data while maintaining an end-to-end latency for updates in the range of a few milliseconds. Third, it illustrates the usage of this engine to detect APT attacks against industries by analyzing IP flow information from an Internet service provider. Finally, it introduces a detection algorithm- and input-agnostic intrusion detection engine which supports not only intrusion detection on IP flow but any other intrusion detection algorithm and data-source as well.

O protocolo International Electrotechnical Commission (IEC)-61850 tornou possível integrar os equipamentos das subestações de energia elétrica, através de uma rede de comunicação de dados Ethernet de alta velocidade. A utilização deste protocolo tem como objetivo principal a interligação dos Intelligent Electronic Devices (IEDs) para a automatização dos processos no sistema elétrico. As contribuições deste protocolo para a integração do controle e supervisão do sistema elétrico são diversas, porém, o fato de utilizar uma rede de comunicação de dados Ethernet integrada expõe o sistema elétrico à ataques cibernéticos. A norma IEC-62351 estabelece uma série de recomendações para prover segurança à rede de comunicação do sistema elétrico, dentre elas, o gerenciamento da rede de comunicação, a análise dos campos da mensagem Generic Object Oriented Substation Event (GOOSE) e a utilização de sistemas de detecção de intrusão. O presente trabalho descreve o desenvolvimento de um Intrusion Detection System (IDS) que atende os requisitos de segurança propostos pelo protocolo IEC-62351, para a identificação de ataques à comunicação realizada por mensagens GOOSE do protocolo IEC-61850, e entre equipamentos do sistema elétrico. Para o desenvolvimento desta aplicação, foram identificados os campos que compõem as mensagens GOOSE, de forma a reconhecer os valores esperados em diferentes situações de operação do sistema elétrico. Determinaram-se padrões de comportamento a serem utilizados para discernir mensagens falsas na rede de comunicação. Instalou-se e configurou-se um sistema operacional de tempo real embarcado na plataforma de desenvolvimento Zynq Board (ZYBO), juntamente com o controlador Open-Mul, para gerenciar a rede de comunicação da subestação, através do protocolo OpenFlow, realizando otimizações para o tráfego multicast. Foi desenvolvido um sistema de detecção e bloqueio de mensagens GOOSE falsas que utiliza o protocolo OpenFlow para controle da rede de comunicação do Sistema Elétrico. Desenvolveu-se ainda um sistema inteligente, utilizando-se uma Rede Neural Artificial (RNA) Nonlinear Autoregressive Model with Exogenous Input (NARX), para predição do tráfego realizado por mensagens GOOSE e detecção de ataques Distributed Deny of Service (DDOS). Os resultados obtidos demonstraram que o protocolo OpenFlow pode ser uma ferramenta interessante para controle da rede, porém, os fabricantes necessitam amadurecer sua implementação nos switches, para que sejam utilizados em produção nas redes de comunicação das subestações. O sistema de predição do tráfego gerado por mensagens GOOSE apresentou benefícios interessantes para a segurança da rede de comunicação, demonstrando potencial para compor um sistema de detecção de ataques DDOS realizado por mensagens GOOSE, na rede de comunicação das subestações de energia elétrica. / The IEC-61850 made it possible to integrate equipments of electric power system substations to a high-speed Ethernet data communication network. Its main goal is the interconnection of IEDs for the automation of processes in an electrical system. The contributions of this protocol for the integration of the control and supervision of the electrical system are diverse, although an Ethernet network exposes the electrical system for cyber attacks. The IEC-62351 states a series of recommendations to provide security to the communication network of the electrical system, such as the communication network management, the analysis of GOOSE messages and the use of intrusion detection systems. This study describes the development of an IDS that meets the security requirements proposed by the IEC-62351 standard to identify attacks on communication between GOOSE messages exchanged by electrical equipment using IEC-61850. For the development of this application, fields of the GOOSE messages were identified, in order to recognize the expected values in different power system operating conditions. Behaviour patterns were determined to detect false messages on the communication network. A real-time embedded operating system on ZYBO was installed and configured, as well as the OpenMul controller to manage the communication network of the substation through the OpenFlow protocol, performing optimizations for multicast traffic. A detection system and block tamper GOOSE messages, using the OpenFlow protocol for control of the electrical system communication network, were developed. In addition, an intelligent system using an Artificial Neural Network (ANN) Nonlinear Autoregressive Model with Exogenous Input (NARX) for predicting of the GOOSE messages traffic and the detection of Distributed Deny of Service attack (DDOS) were also developed. The results obtained show that the OpenFlow protocol may be a valuable tool for network control, however, manufacturers should maturely carry on with its implementation in the switches, so that it be used in substation communication networks. The traffic prediction system of the GOOSE messages presented interesting benefits for the security of the communication network, demonstrating potential to built a DDOS attack detection system performed by GOOSE messages on the communication network of electric power substations.