Biblio

Due to the rapid development of cyber-physical systems, there are more and more security problems. The purpose of this work is to develop the concept of a knowledge base in the field of security of cyber-physical systems based on an ontological approach. To create the concept of a knowledge base, it was necessary to consider the system of a cyber-physical system and highlight its structural parts. As a result, the main concepts of the security of a cyber-physical system were identified and the concept of a knowledge base was drawn up, which in the future will help to analyze potential threats to cyber-physical systems.

Recent advances in deep learning typically, with the introduction of transformer based models has shown massive improvement and success in many Natural Language Processing (NLP) tasks. One such area which has leveraged immensely is conversational agents or chatbots in open-ended (chit-chat conversations) and task-specific (such as medical or legal dialogue bots etc.) domains. However, in the era of automation, there is still a dearth of works focused on one of the most relevant use cases, i.e., tutoring dialog systems that can help students learn new subjects or topics of their interest. Most of the previous works in this domain are either rule based systems which require a lot of manual efforts or are based on multiple choice type factual questions. In this paper, we propose EDICA (Educational Domain Infused Conversational Agent), a language tutoring Virtual Agent (VA). EDICA employs two mechanisms in order to converse fluently with a student/user over a question and assist them to learn a language: (i) Student/Tutor Intent Classification (SIC-TIC) framework to identify the intent of the student and decide the action of the VA, respectively, in the on-going conversation and (ii) Tutor Response Generation (TRG) framework to generate domain infused and intent/action conditioned tutor responses at every step of the conversation. The VA is able to provide hints, ask questions and correct student's reply by generating an appropriate, informative and relevant tutor response. We establish the superiority of our proposed approach on various evaluation metrics over other baselines and state of the art models.

Operating systems are essential software components for any computer. The goal of computer system manu-facturers is to provide a safe operating system that can resist a range of assaults. APTs (Advanced Persistent Threats) are merely one kind of attack used by hackers to penetrate organisations (APT). Here, we will apply the MITRE ATT&CK approach to analyze the security of Windows and Linux. Using the results of a series of vulnerability tests conducted on Windows 7, 8, 10, and Windows Server 2012, as well as Linux 16.04, 18.04, and its most current version, we can establish which operating system offers the most protection against future assaults. In addition, we have shown adversarial reflection in response to threats. We used ATT &CK framework tools to launch attacks on both platforms.

While digitization of distribution grids through information and communications technology brings numerous benefits, it also increases the grid's vulnerability to serious cyber attacks. Unlike conventional systems, attacks on many industrial control systems such as power grids often occur in multiple stages, with the attacker taking several steps at once to achieve its goal. Detection mechanisms with situational awareness are needed to detect orchestrated attack steps as part of a coherent attack campaign. To provide a foundation for detection and prevention of such attacks, this paper addresses the detection of multi-stage cyber attacks with the aid of a graph-based cyber intelligence database and alert correlation approach. Specifically, we propose an approach to detect multi-stage attacks by lever-aging heterogeneous data to form a knowledge base and employ a model-based correlation approach on the generated alerts to identify multi-stage cyber attack sequences taking place in the network. We investigate the detection quality of the proposed approach by using a case study of a multi-stage cyber attack campaign in a future-orientated power grid pilot.

Currently, many organizations are moving to new digital management systems, which is accompanied not only by the introduction of new approaches based on the use of information technology, but also by a change in the organizational and management environment. Risk management is a process necessary to maintain the competitive advantage of an organization, but it can also become involved in the course of digitalization itself, which means that risk management also needs to change to meet modern conditions and ensure the effectiveness of the organization. This article discusses the risk management process in the digital environment. The main approach to the organization of this process is outlined, taking into account the use of information tools, together with the stages of this process, which directly affect the efficiency of the company. The risks that are specific to a digital organization are taken into account. Modern requirements for risk management for organizations are studied, ways of their implementation are outlined. The result is a risk management process that functions in a digital organization.

We propose an approach for filtering and prioritizing static code analysis alerts while these alerts are being reviewed by the developer. We construct a Prolog knowledge base that captures the data flow information in the source code as well as the reported alerts, their properties and associations with the data flow. The knowledge base is updated as the developer reviews the listed alerts and decides whether they point at an actual fault or not. These updates provide useful information since some of the alerts of the same type can be related in terms of their root cause. Hence, dynamically updated knowledge base can be queried to eliminate or prioritize the remaining alerts in the review list. We present a motivating example to illustrate the approach and its automation by integrating a set of tools.

Data on software vulnerabilities, products and exploits is typically collected from multiple non-structured sources. Valuable information, e.g., on which products are affected by which exploits, is conveyed by matching data from those sources, i.e., through their relations. In this paper, we leverage this simple albeit unexplored observation to introduce a statistical relational learning (SRL) approach for the analysis of vulnerabilities, products and exploits. In particular, we focus on the problem of determining the existence of an exploit for a given product, given information about the relations between products and vulnerabilities, and vulnerabilities and exploits, focusing on Industrial Control Systems (ICS), the National Vulnerability Database and ExploitDB. Using RDN-Boost, we were able to reach an AUC ROC of 0.83 and an AUC PR of 0.69 for the problem at hand. To reach that performance, we indicate that it is instrumental to include textual features, e.g., extracted from the description of vulnerabilities, as well as structured information, e.g., about product categories. In addition, using interpretable relational regression trees we report simple rules that shed insight on factors impacting the weaponization of ICS products.

The interdisciplinary field of immersive learning research is scattered. Combining efforts for better exploration of this field from the different disciplines requires researchers to communicate and coordinate effectively. We call upon the community of immersive learning researchers for planting the Knowledge Tree of Immersive Learning Research, a proposal for a systematization effort for this field, combining both scholarly and practical knowledge, cultivating a robust and ever-growing knowledge base and methodological toolbox for immersive learning. This endeavor aims at promoting evidence-informed practice and guiding future research in the field. This paper contributes with the rationale for three objectives: 1) Developing common scientific terminology amidst the community of researchers; 2) Cultivating a common understanding of methodology, and 3) Advancing common use of theoretical approaches, frameworks, and models.

Cloud-based enterprise search services (e.g., AWS Kendra) have been entrancing big data owners by offering convenient and real-time search solutions to them. However, the problem is that individuals and organizations possessing confidential big data are hesitant to embrace such services due to valid data privacy concerns. In addition, to offer an intelligent search, these services access the user’s search history that further jeopardizes his/her privacy. To overcome the privacy problem, the main idea of this research is to separate the intelligence aspect of the search from its pattern matching aspect. According to this idea, the search intelligence is provided by an on-premises edge tier and the shared cloud tier only serves as an exhaustive pattern matching search utility. We propose Smartness at Edge (SAED mechanism that offers intelligence in the form of semantic and personalized search at the edge tier while maintaining privacy of the search on the cloud tier. At the edge tier, SAED uses a knowledge-based lexical database to expand the query and cover its semantics. SAED personalizes the search via an RNN model that can learn the user’s interest. A word embedding model is used to retrieve documents based on their semantic relevance to the search query. SAED is generic and can be plugged into existing enterprise search systems and enable them to offer intelligent and privacy-preserving search without enforcing any change on them. Evaluation results on two enterprise search systems under real settings and verified by human users demonstrate that SAED can improve the relevancy of the retrieved results by on average ≈24% for plain-text and ≈75% for encrypted generic datasets.

Firewall is the first defense line for network security. Packet filtering is a basic function in firewall, which filter network packets according to a series of rules called firewall policy. The design of firewall policy is invariably under the instruction of security policy, which is a generic guideline that lists the needs for network access permissions. The design of firewall policy should observe the regulations of security policy. However, even for IPv4 firewall policy, it is extremely difficult to keep the consistency between security policy and firewall policy. Some consistency decision methods of security policy and IPv4 firewall policy were proposed. However, the address space of IPv6 address is a very large, the existing consistency decision methods can not be directly used to deal with IPv6 firewall policy. To resolve the above problem, in this paper, we use a formal technique to decide the consistency between IPv6 firewall policy and security policy effectively and rapidly. We also developed a prototype model and evaluated the effectiveness of the proposed method.

Endpoint Detection and Response (EDR) tools provide visibility into sophisticated intrusions by matching system events against known adversarial behaviors. However, current solutions suffer from three challenges: 1) EDR tools generate a high volume of false alarms, creating backlogs of investigation tasks for analysts; 2) determining the veracity of these threat alerts requires tedious manual labor due to the overwhelming amount of low-level system logs, creating a "needle-in-a-haystack" problem; and 3) due to the tremendous resource burden of log retention, in practice the system logs describing long-lived attack campaigns are often deleted before an investigation is ever initiated.This paper describes an effort to bring the benefits of data provenance to commercial EDR tools. We introduce the notion of Tactical Provenance Graphs (TPGs) that, rather than encoding low-level system event dependencies, reason about causal dependencies between EDR-generated threat alerts. TPGs provide compact visualization of multi-stage attacks to analysts, accelerating investigation. To address EDR's false alarm problem, we introduce a threat scoring methodology that assesses risk based on the temporal ordering between individual threat alerts present in the TPG. In contrast to the retention of unwieldy system logs, we maintain a minimally-sufficient skeleton graph that can provide linkability between existing and future threat alerts. We evaluate our system, RapSheet, using the Symantec EDR tool in an enterprise environment. Results show that our approach can rank truly malicious TPGs higher than false alarm TPGs. Moreover, our skeleton graph reduces the long-term burden of log retention by up to 87%.

Within a framework for verifying parametric network protocols through induction, one needs to find invariants based on a protocol instance of a small number of nodes. In this paper, we propose a new approach to accelerate parameterized verification by adopting decision trees to represent the state space of a protocol instance. Such trees can be considered as a knowledge base that summarizes all behaviors of the protocol instance. With this knowledge base, we are able to efficiently construct an oracle to effectively assess candidates of invariants of the protocol, which are suggested by an invariant finder. With the discovered invariants, a formal proof for the correctness of the protocol can be derived in the framework after proper generalization. The effectiveness of our method is demonstrated by experiments with typical benchmarks.

Visual reasoning between visual image and natural language description is a long-standing challenge in computer vision. While recent approaches offer a great promise by compositionality or relational computing, most of them are oppressed by the challenge of training with datasets containing only a limited number of images with ground-truth texts. Besides, it is extremely time-consuming and difficult to build a larger dataset by annotating millions of images with text descriptions that may very likely lead to a biased model. Inspired by the majority success of webly supervised learning, we utilize readily-available web images with its noisy annotations for learning a robust representation. Our key idea is to presume on web images and corresponding tags along with fully annotated datasets in learning with knowledge embedding. We present a two-stage approach for the task that can augment knowledge through an effective embedding model with weakly supervised web data. This approach learns not only knowledge-based embeddings derived from key-value memory networks to make joint and full use of textual and visual information but also exploits the knowledge to improve the performance with knowledge-based representation learning for applying other general reasoning tasks. Experimental results on two benchmarks show that the proposed approach significantly improves performance compared with the state-of-the-art methods and guarantees the robustness of our model against visual reasoning tasks and other reasoning tasks.

Cloud security is one of the major issues that worry individuals and organizations about cloud computing. Therefore, defending cloud systems against attacks such asinsiders' attacks has become a key demand. This paper investigates insider threat in cloud relational database systems(cloud RDMS). It discusses some vulnerabilities in cloud computing structures that may enable insiders to launch attacks, and shows how load balancing across multiple availability zones may facilitate insider threat. To prevent such a threat, the paper suggests three models, which are Peer-to-Peer model, Centralized model and Mobile-Knowledgebase model, and addresses the conditions under which they work well.

Taking care of security at the cloud is a major issue that needs to be carefully considered and solved for both individuals as well as organizations. Organizations usually expect more trust from employees as well as customers in one hand. On the other hand, cloud users expect their private data is maintained and secured. Although this must be case, however, some malicious outsiders of the cloud as well as malicious insiders who are cloud internal users tend to disclose private data for their malicious uses. Although outsiders of the cloud should be a concern, however, the more serious problems come from Insiders whose malicious actions are more serious and sever. Hence, insiders' threats in the cloud should be the top most problem that needs to be tackled and resolved. This paper aims to find a proper solution for the insider threat problem in the cloud. The paper presents a Mobile Edge Computing (MEC) mitigation model as a solution that suits the specialized nature of this problem where the solution needs to be very close to the place where insiders reside. This in fact gives real-time responses to attack, and hence, reduces the overhead in the cloud.

The objective of this paper is to propose a model of a distributed intrusion detection system based on the multi-agent paradigm and the distributed file system (HDFS). Multi-agent systems (MAS) are very suitable to intrusion detection systems as they can address the issue of geographic data security in terms of autonomy, distribution and performance. The proposed system is based on a set of autonomous agents that cooperate and collaborate with each other to effectively detect intrusions and suspicious activities that may impact geographic information systems. Our system allows the detection of known and unknown computer attacks without any human intervention (Security Experts) unlike traditional intrusion detection systems that rely on knowledge bases as a mechanism to detect known attacks. The proposed model allows a real time detection of known and unknown attacks within large networks hosting geographic data.

File timestamps do not receive much attention from information security specialists and computer forensic scientists. It is believed that timestamps are extremely easy to fake, and the system time of a computer can be changed. However, operating system for synchronizing processes and working with file objects needs accurate time readings. The authors estimate that several million timestamps can be stored on the logical partition of a hard disk with the NTFS. The MFT stores four timestamps for each file object in \$STANDARDİNFORMATION and \$FILE\_NAME attributes. Furthermore, each directory in the İNDEX\_ROOT or İNDEX\_ALLOCATION attributes contains four more timestamps for each file within it. File timestamps are set and changed as a result of file operations. At the same time, some file operations differently affect changes in timestamps. This article presents the results of the tool-based observation over the creation and update of timestamps in the MFT resulting from the basic file operations. Analysis of the results is of interest with regard to computer forensic science.

This paper describes research results of the possibility of developing a methodology to implement systematic knowledge about adversaries` tactics and techniques into the process of determining requirements for information security system and evaluating defensive countermeasures.

This paper describes a machine assistance approach to grading decisions for values that might be missing or need validation, using a mathematical algebraic form of an Expert System, instead of the traditional textual or logic forms and builds a neural network computational graph structure. This Experts System approach is also structured into a neural network like format of: input, hidden and output layers that provide a structured approach to the knowledge-base organization, this provides a useful abstraction for reuse for data migration applications in big data, Cyber and relational databases. The approach is further enhanced with a Bayesian probability tree approach to grade the confidences of value probabilities, instead of the traditional grading of the rule probabilities, and estimates the most probable value in light of all evidence presented. This is ground work for a Machine Learning (ML) experts system approach in a form that is closer to a Neural Network node structure.

The aim of this research paper is to highlight the intellectual property place and role within an industrial knowledge-based organization which performs design activities. The research begins by presenting the importance of integrating intellectual property policy implementation with quality policy. The research is based on the setting of objectives in the intellectual property field. This research also establishes some intellectual property strategies, and improvement measures for intellectual property protection management. The basis for these activities is correlation of the quality policy with an intellectual property policy, as well as the point of strength identified in the studied organization. The issues discussed in this scientific paper conclude on the possibility of the implementation of standards in the intellectual property field.

Failure to detect malware at its very inception leaves room for it to post significant threat and cost to cyber security for not only individuals, organizations but also the society and nation. However, the rapid growth in volume and diversity of malware renders conventional detection techniques that utilize feature extraction and comparison insufficient, making it very difficult for well-trained network administrators to identify malware, not to mention regular users of internet. Challenges in malware detection is exacerbated since complexity in the type and structure also increase dramatically in these years to include source code, binary file, shell script, Perl script, instructions, settings and others. Such increased complexity offers a premium on misjudgment. In order to increase malware detection efficiency and accuracy under large volume and multiple types of malware, this research adopts Convolutional Neural Networks (CNN), one of the most successful deep learning techniques. The experiment shows an accuracy rate of over 90% in identifying malicious and benign codes. The experiment also presents that CNN is effective with detecting source code and binary code, it can further identify malware that is embedded into benign code, leaving malware no place to hide. This research proposes a feasible solution for network administrators to efficiently identify malware at the very inception in the severe network environment nowadays, so that information technology personnel can take protective actions in a timely manner and make preparations for potential follow-up cyber-attacks.

In this research paper author surveys the need of data protection from intelligent systems in the private and public sectors. For this, she identifies that the Smart Information Security Intel processes needs to be the suggestive key policy for both sectors of governance either public or private. The information is very sensitive for any organization. When the government offices are concerned, information needs to be abstracted and encapsulated so that there is no information stealing. For this purposes, the art of skill set and new optimized technology needs to be stationed. Author identifies that digital bar-coded air port like security using conveyor belts and digital bar-coded conveyor boxes to scan switched ON articles like internet of things needs to be placed. As otherwise, there can potentially be data, articles or information stealing from the operational sites where access is unauthorized. Such activities shall need to be scrutinized, minutely. The biometric such as fingerprints, iris, voice and face recognition pattern updates in the virtual data tables must be taken to keep data entry-exit log up to-date. The information technicians of the sentinel systems must help catch the anomalies in the professional working time in private and public sectors if there is red flag as indicator. The author in this research paper shall discuss in detail what we shall station, how we shall station and what all measures we might need to undertake to safeguard the stealing of sensitive information from the organizations like administration buildings, government buildings, educational schools, hospitals, courts, private buildings, banks and all other offices nation-wide. The TO-BE new processes shall make the AS-IS office system more information secured, data protected and personnel security stronger.

Continuously growing amount of research experiments using High Performance Computing (HPC) leads to the questions of research data management and in particular how to preserve a scientific experiment including all related data for long term for its future reproduction. This paper covers some challenges and possible solutions related to the preservation of scientific experiments on HPC systems and represents a concept of the preservation system for HPC computations. Storage of the experiment itself with some related data is not only enough for its future reproduction, especially in the long term. For that case preservation of the whole experiment's environment (operating system, used libraries, environment variables, input data, etc.) via containerization technology (e.g. using Docker, Singularity) is proposed. This approach allows to preserve the entire environment, but is not always possible on every HPC system because of security issues. And it also leaves a question, how to deal with commercial software that was used within the experiment. As a possible solution we propose to run a preservation process outside of the computing system on the web-server and to replace all commercial software inside the created experiment's image with open source analogues that should allow future reproduction of the experiment without any legal issues. The prototype of such a system was developed, the paper provides the scheme of the system, its main features and describes the first experimental results and further research steps.

The work defines a multi-factor authentication model in case the application supports multiple authentication factors. The aim of this modeling is to find acceptable authentication methods sufficient to access specifically qualified information. The core of the proposed model is risk-based authentication. Results of simulations of some key scenarios often used in practice are also presented.

We investigate a method of building a closed domain intelligent conversational agent using deep neural networks. A conversational agent is a dialog system intended to converse with a human, with a coherent structure. Our conversational agent uses a retrieval based model that identifies the intent of the input user query and maps it to a knowledge base to return appropriate results. Human conversations are based on context, but existing conversational agents are context insensitive. To overcome this limitation, our system uses a simple stack based context identification and storage system. The conversational agent generates responses according to the current context of conversation. allowing more human-like conversations.