Biblio

Advanced Persistent Threats (APTs) refer to sophisticated, prolonged and multi-step attacks, planned and executed by skilled adversaries targeting government and enterprise networks. Attack graphs' topologies can be leveraged to detect, explain and visualize the progress of such attacks. However, due to the abundance of false-positives, such graphs are usually overwhelmingly large and difficult for an analyst to understand. Graph partitioning refers to the problem of reducing the graph of alerts to a set of smaller incidents that are easier for an analyst to process and better represent the actual attack plan. Existing approaches are oblivious to the security-context of the problem at hand and result in graphs which, while smaller, make little sense from a security perspective. In this paper, we propose an optimization approach allowing us to generate security-aware partitions, utilizing aspects such as the kill chain progression, number of assets involved, as well as the size of the graph. Using real-world datasets, the results show that our approach produces graphs that are better at capturing the underlying attack compared to state-of-the-art approaches and are easier for the analyst to understand.

The popularity of web applications and their world-wide use to support business critical operations raised the interest of hackers on exploiting security vulnerabilities to perform malicious operations. Fostering trust calls for assessment techniques that provide indicators about the quality of a web application from a security perspective. This paper studies the problem of using coding practices to characterize the trustworthiness of web applications from a security perspective. The hypothesis is that applying feasible security practices results in applications having a reduced number of unknown vulnerabilities, and can therefore be considered more trustworthy. The proposed approach is instantiated for the concrete case of input validation practices, and includes a Quality Model to compute trustworthiness scores that can be used to compare different applications or different code elements in the same application. Experimental results show that the higher scores are obtained for more secure code, suggesting that it can be used in practice to characterize trustworthiness, also providing guidance to compare and/or improve the security of web applications.

The low attention to security and privacy causes some problems on data and information that can lead to a lack of public trust in e-Gov service. Security threats are not only included in technical issues but also non-technical issues and therefore, it needs the implementation of inclusive security. The application of inclusive security to e-Gov needs to develop a model involving security and privacy requirements as a trusted security solution. The method used is the elicitation of security and privacy requirements in a security perspective. Identification is carried out on security and privacy properties, then security and privacy relationships are determined. The next step is developing the design of an inclusive security model on e-Gov. The last step is doing an analysis of e-Gov service activities and the role of inclusive security. The results of this study identified security and privacy requirements for building inclusive security. Identification of security requirements involves properties such as confidentiality (C), integrity (I), availability (A). Meanwhile, privacy requirement involves authentication (Au), authorization (Az), and Non-repudiation (Nr) properties. Furthermore, an inclusive security design model on e-Gov requires trust of internet (ToI) and trust of government (ToG) as an e-Gov service provider. Access control is needed to provide solutions to e-Gov service activities.

Living in the age of digital transformation, companies and individuals are moving to public and private clouds to store and retrieve information, hence the need to store and retrieve data is exponentially increasing. Existing storage technologies such as DAS are facing a big challenge to deal with these huge amount of data. Hence, newer technologies should be adopted. Storage Area Network (SAN) is a distributed storage technology that aggregates data from several private nodes into a centralized secure place. Looking at SAN from a security perspective, clearly physical security over multiple geographical remote locations is not adequate to ensure a full security solution. A SAN security framework needs to be developed and designed. This work investigates how SAN protocols work (FC, ISCSI, FCOE). It also investigates about other storages technologies such as Network Attached Storage (NAS) and Direct Attached Storage (DAS) including different metrics such as: IOPS (input output per second), Throughput, Bandwidths, latency, cashing technologies. This research work is focusing on the security vulnerabilities in SAN listing different attacks in SAN protocols and compare it to other such as NAS and DAS. Another aspect of this work is to highlight performance factors in SAN in order to find a way to improve the performance focusing security solutions aimed to enhance the security level in SAN.

Internet of Things (IoT) device authentication is weighed as a very important step from security perspective. Privacy and security of the IoT devices and applications is the major issue. From security perspective, important issue that needs to be addressed is the authentication mechanism, it has to be secure from different types of attacks and is easy to implement. The paper gives general idea about how different authentication mechanisms work, and then secure and efficient multi-factor device authentication scheme idea is proposed. The proposed scheme idea uses digital signatures and device capability to authenticate a device. In the proposed scheme device will only be allowed into the network if it is successfully authenticated through multi-factor authentication otherwise the authentication process fails and whole authentication process will restart. By analyzing the proposed scheme idea, it can be seen that the scheme is efficient and has less over head. The scheme not only authenticates the device very efficiently through multi-factor authentication but also authenticates the authentication server with the help of digital signatures. The proposed scheme also mitigates the common attacks like replay and man in the middle because of nonce and timestamp.

Internet of Things (IoT) and 5G are emerging technologies that prompt a mobile service platform capable of provisioning billions of communication devices which enable ubiquitous computing and ambient intelligence. These novel approaches are guaranteeing gigabit-level bandwidth, ultra-low latency and ultra-high storage capacity for their subscribers. To achieve these limitations, ETSI has introduced the paradigm of Multi-Access Edge Computing (MEC) for creating efficient data processing architecture extending the cloud computing capabilities in the Radio Access Network (RAN). Despite the gained enhancements to the mobile network, MEC is subjected to security challenges raised from the heterogeneity of IoT services, intricacies in integrating virtualization technologies, and maintaining the performance guarantees of the mobile networks (i.e. 5G). In this paper, we are identifying the probable threat vectors in a typical MEC deployment scenario that comply with the ETSI standards. We analyse the identified threat vectors and propose solutions to mitigate them.

In this paper, cyber physical system is analyzed from security perspective. A double closed-loop security control structure and algorithm with defense functions is proposed. From this structure, the features of several cyber attacks are considered respectively. By this structure, the models of information disclosure, denial-of-service (DoS) and Man-in-the-Middle Attack (MITM) are proposed. According to each kind attack, different models are obtained and analyzed, then reduce to the unified models. Based on this, system security conditions are obtained, and a defense scenario with detail algorithm is design to illustrate the implementation of this program.

Wireless Sensor Network (WSN) are spread everywhere throughout the world and are ordinarily used to gather physical data from the encompassing scene. WSN play a focal part in the Internet of Things (IoT) vision. WSN is rising as a noticeable component in the middleware connecting together the Internet of Things (IoT) and the Web of Things (WoT). But the integration of WSN to WoT brings new challenges that cannot be solved in a satisfactory way with traditional layer of security. This paper examined the security issue of integration between WSN and WoT, aiming to shed light on how the WSN and WoT security issue are understood and applied, both in academia and industries. This paper introduces security perfective of integration WSN to WoT which offers capabilities to identify and connect worldwide physical objects into a unified system. As a part of the integration, serious concerns are raised over access of personal information pertaining to device (smart thing) and individual privacy. The motivation of this paper is to summarizes the security threats of the integration and suggestion to mitigate the threat.

Threat classification is extremely important for individuals and organizations, as it is an important step towards realization of information security. In fact, with the progress of information technologies (IT) security becomes a major challenge for organizations which are vulnerable to many types of insiders and outsiders security threats. The paper deals with threats classification models in order to help managers to define threat characteristics and then protect their assets from them. Existing threats classification models are non complete and present non orthogonal threats classes. The aim of this paper is to suggest a scalable and complete approach that classifies security threat in orthogonal way.

Today's systems produce a rapidly exploding amount of data, and the data further derives more data, forming a complex data propagation network that we call the data's lineage. There are many reasons that users want systems to forget certain data including its lineage. From a privacy perspective, users who become concerned with new privacy risks of a system often want the system to forget their data and lineage. From a security perspective, if an attacker pollutes an anomaly detector by injecting manually crafted data into the training data set, the detector must forget the injected data to regain security. From a usability perspective, a user can remove noise and incorrect entries so that a recommendation engine gives useful recommendations. Therefore, we envision forgetting systems, capable of forgetting certain data and their lineages, completely and quickly. This paper focuses on making learning systems forget, the process of which we call machine unlearning, or simply unlearning. We present a general, efficient unlearning approach by transforming learning algorithms used by a system into a summation form. To forget a training data sample, our approach simply updates a small number of summations – asymptotically faster than retraining from scratch. Our approach is general, because the summation form is from the statistical query learning in which many machine learning algorithms can be implemented. Our approach also applies to all stages of machine learning, including feature selection and modeling. Our evaluation, on four diverse learning systems and real-world workloads, shows that our approach is general, effective, fast, and easy to use.