Malicious Objects Research Articles

A Machine Learning Approach Towards Cyber-Physical Security of Battery Systems

Abstract Modern battery systems exhibit a cyber-physical nature due to the extensive use of communication technologies in battery management. This makes modern cyber-physical battery systems vulnerable to cyber threats where an adversary can manipulate sensing and actuation signals to satisfy certain malicious objectives. In this work, we present a machine learning-based approach to enable resilience to adversarial attacks by detecting and estimating the attack and subsequently taking corrective action to mitigate the attack. In particular, we focus on false data injection type attacks on battery systems. The overall diagnostic algorithm consists of an adaptive boosting-based attack detector, a Long Short Term Memory (LSTM) neural network-based attack estimator, and a corrective controller. The proposed algorithm is trained and tested by utilizing data from a complex battery electrochemical battery simulator. Simulation results are presented to verify the effectiveness of the approach.

Interconnected Takagi-Sugeno system and fractional SIRS malware propagation model for stabilization of Wireless Sensor Networks

This paper is devoted to investigate the dynamical behaviors of malware attack on a familiar kind of complex heterogeneous networks, namely Wireless Sensor Network, and discuss an effective immunization treatment based on fractional interconnected Takagi-Sugeno (T-S) fuzzy systems. Our approach is based on the mathematical modeling to establish a controlled fractional network-based SIRS malware propagation model that better describes the attacking behavior of malicious objects on Wireless Sensor Network. After that, we point out some qualitative properties of the proposed network-based SIRS malware propagation model such as the existence of positively invariant set, backward bifurcation and asymptotic behavior. Especially, in order to study the model's stability, we evaluate an epidemiological threshold value R0, namely basic reproductive ratio, which ensures the existence of at least one endemic equilibrium P⁎ and the local asymptotic stability of malware-free equilibrium P0. As a consequence of theoretical result, the malware-free equilibrium P0 is unstable when R0>1 and hence, the rest of this paper is to address a stabilization problem for the proposed controlled network-based model and establish some sufficient conditions related to linear matrix inequalities and positive definite matrices. Finally, we illustrate the obtained theoretical results by a computational example.

Enhanced trust management for building trustworthy social internet of things network

AbstractInternet of Things (IoT) and wireless communication technologies are evolving rapidly and changing the way we live and work. IoT devices may need to share personal information over the public network taking the help of nearby devices. Thus, the trustworthiness of nearby devices shall play an essential role in providing security and privacy assurance. The authors proposed an autonomous decentralised trust management model for selecting a trustworthy device for a requested service transaction. The proposed scheme uses the Social Internet of Things for trust management. The proposed model uses social relationships to find the level of trust among related devices, estimate the overall trust of the unknown devices, periodically update the observed trust values, and isolate the malicious nodes in the network. The evaluated trust values are updated in the network frequently so that other devices can utilise the information later. The periodic update can increase performance and detect trust‐related malicious attacks. The simulation result shows that the performance of the proposed model is better as compared to existing trust management models. The proposed model can detect malicious objects at an early stage and can handle malicious attacks by isolating malicious devices.

Model for the Propagation of Malicious Objects in a Computer Network with Variable Infection Intensity

There are a significant number of scientific publications that use epidemic models to propagate malicious objects in a computer network. These models are based on Markovian models with a constant intensity of transitions, which does not correspond to real conditions, since the intensity of transitions changes due to the fact that after some time antivirus systems start to recognize malware. This paper proposes an original approach based on an epidemic model with variable infection intensity of hosts in a computer network. In the beginning, when the threat is not recognized, the malware spreads rapidly. After a certain period of time, the antivirus system recognizes the malicious code, which leads to a decrease in the infection intensity. Simulations have been done for different infection intensity and threat recognition. Demonstrated models account for the infection time of hosts in the computer network, latency phase, malware detection, and clearance from the system.

The performance evolution of antivirus security systems in ultradense cloud server using intelligent deep learning

When creating an antivirus, not only the latest security mechanisms are taken into account, but also the needs of users. That’s why this antivirus works together at high speed. The program interface allows it to choose the most optimal function. Free delivery allows a large number of users to rate this product. With the help of an intelligent deep learning model, a smart solution was proposed in this article to identify the security threats. It enables rapid detection and efficient treatment of polymorphic and encrypted viruses. Infected archives can now be detected when opened. This helps prevent its software from getting infected again. The program has the ability to create a confidence zone, which allows reducing the scanning time by creating a list of objects subject to scanning. This list should only contain sources that you are sure of. This application is designed to provide reliable protection for your computer. The proposed model allows it to protect its computer from all types of viruses and various Trojans, root kits, worms, and other malicious objects.

Computer Intelligence in Higher Education

The role of artificial intelligence (AI) systems is constantly increasing in the creation and production of this knowledge. Software and hardware complexes of universal humanoid intelligence and artificial superintelligence are being created with maximum intensity. Progress in this field in the last 15 years is reflected precisely in the realization that the human intellect does not arise simply from a few methods and techniques for solving problems, schemes, and reasoning mechanisms, but requires the use of specific knowledge depending on the specific problem area. Education, thanks to the application of modern technologies, is no longer a privilege, but a basic human right.

Malevolent Information Crawling Mechanism for Forming Structured Illegal Organisations in Hidden Networks

Terrorist groups like ISIS have made considerable use of the dark web (DW) to carry out their malicious objectives such as spreading propaganda, recruiting and radicalizing new recruits, and secretly raising finances. Al-Hayat Media Center, an ISIS media agency, released a link on their forum describing how to access their DW website. It also sent out the identical message over Telegram, which included links to a Tor service with a “.onion” address. This study develops an analytical framework for scraping and analyzing the DW on the internet. The authors successfully tested a web crawler to collect account information for thousands of merchants and their related marketplace listings using a case study marketplace. The paper explains how to scrape DW marketplaces in the most viable and effective way possible. The findings of the case study support the validity of the proposed analytical framework, which is useful for academics researching this emerging phenomena as well as investigators looking into illegal behavior on the DW.

Malware and Malware Detection Techniques: A Survey

Abstract: Malicious software is a kind of software or codes which took some: private data, information from the PC framework, its tasks is to do only malicious objectives to the PC framework, without authorization of the PC clients. The effect of malicious software are worsen to the client. Malicious software i.e malwares are programs that are made to mischief, hinder or harm PCs, organizations and different assets related with it. Malwares are moved in PCs without the information on its proprietor. Presently malicious program is a serious threat. It is created to harm the PC framework and some of them are spread over the associated framework in the organization or web association. Analysts are making great efforts in malware framework field with compelling malware detection techniques to safeguard PC framework. Two essential methodologies have been proposed for it for example signature-based and heuristic-based detection. These methodologies distinguish known malware precisely yet can't distinguish the new, obscure malware. Recently various analysts have proposed malware identification framework utilizing data mining and machine learning strategies to distinguish between obscure and non – obscure malwares. In this paper, an detailed examination has been led on the present status of malware infection and work done for finding it. Keywords: PC framework, malicious software, heuristic-based , signature – based , zero -day malware , obscure malware

Prediction of malicious objects using prey-predator model in Internet of Things (IoT) for smart cities

Presently, the interconnected networks in smart cities are increasing at a high pace using the Internet of Things (IoT), which allows the user to access the device from anywhere and gather the data. With such massive networks, data analysis plays a vital role in the real world to interpret and analyze the information, giving it a meaningful form. Such an extensive network of interconnected devices leads to a high probability of information theft and data alteration/manipulation through malicious attacks, leading to incorrect information floating over the network, resulting in misleading analysis. This may result is significant disaster in FOG computing environment resulting in failure of smart city applications like healthcare, smart traffic and many more. So, to over a model is required to identify the behaviors of attacker/malicious node. Many work are been proposed using clustering, game theory, fuzzy logic and Intrusion Detection System (IDS) to solve this but they do not consider the spread of infection affecting the other nodes. In this work a pre-predator model to determine the malicious node in the network has been proposed. The model consists prey and predator, where prey consists of infected nodes, whereas predators are malicious objects. In IoT networks, the delay is not the real factor in the spread of infection due to the chaotic nature of the malicious objects. So to overcome this issue, delay differential equation modeling is used.The performance of proposed model is compared with fuzzy logic and game theory based existing models taking into time to detect malicious, rate of infection and Count of infected node detected as performance parameters. Results shows 5% and 8% reduction in number of infected nodes as compared to fuzzy logic and game theory-based approach and reduction of 9% in infection rate.

Protecting Routing Data in WSNs with use of IOTA Tangle

Routing in wireless sensor networks (WSNs) are based on multi-hop communication in which the messages pass through multiple sensor nodes, and hence routing algorithms must rely on trust relationships between neighboring nodes. The open access nature of WSNs leads to the possibility of nodes becoming compromised and consequently being turned into malicious objects. One such attack on WSNs is the Sybil attack, in which an attacker can take control of a legitimate node or enter a malicious node into the network and create fake identities. Consequently, they can change the behavior of the WSN, such as its routing schema to cause loops or wrong directions to manipulate data and consume the energy of the network, or even target cluster heads. In this paper, we present a novel technique based on IOTA Tangle, a distributed ledger technology, for the detection and prevention of Sybil attacks by protecting routing data. A transaction history on IOTA is maintained for detecting malicious node injection, and IOTA currency is used as a reputation score to prevent malicious nodes and protect the routing table. Even if an attacker gains access to the network, all routing data can be tracked in IOTA Tangle that will alert the base station about this attack. The technique has been simulated and evaluated using a proof-of-concept prototype.

ConTrust: A Novel Context-Dependent Trust Management Model in Social Internet of Things

The global population is around 7.4 billion people. This population density requires connectivity to improve the standard of living by transmitting and receiving variety of services. As a result, numerous forms of communication among objects are required for our everyday living demands, independent of their nature. Furthermore, to create a good relationship, every object that is regarded as associate of another object should have distinct criteria such as scalability, interoperability, and trustworthiness. Many security threats, however, have an impact on the social interaction between objects in a social internet of things (SIoT) context, including illegal admittance and suspicious behavior owing to a lack of verification architecture. Others include attempting to provide a proper viewpoint of a malicious object to earn the trust of other objects. As a result, there is a requirement for an acceptable method to check the behavior of objects such as capability, commitment, reliability, and previous job satisfaction before proceeding with any type of job assignment. This will aid in distinguishing between malicious and trustworthy objects by anticipating their upcoming behavior, allowing better judgments regarding service assignment to be made. This study proposes a context-dependent trust management technique (ConTrust) for choosing and allocating jobs in a SIoT environment. The feature-property match approach, as well as the combination of capability, commitment, and satisfaction, were utilized to increase the efficiency of trust assessment and the resolution of context-dependent difficulties. The proposed trust model considers job characteristics, object capabilities and honesty, and the impact of malicious conduct. The experimental results show that the proposed ConTrust model is viable and capable of ensuring the reliability and efficacy of SIoT service sharing between objects as compared to the benchmark models considered in this work.

The fight against malware as a service

Malware developers and distributors wasted no time in exploiting the Covid-19 pandemic for their own malicious objectives. In 2020, the number of new malware samples nearly doubled compared with 2019. 1 More concerningly, cyber criminals are also becoming smarter. Rather than merely relying upon a larger quantity of threats, they are also leveraging technology innovations to grow their criminal organisations and generate new revenue streams.

Security and Trust Model Analysis for Banking System

Background: There are mainly three types of banking includes Traditional banking, online banking, and mobile banking. The use of the latter two i.e, online banking and mobile banking, over traditional methods should rise exponentially among the people. This will be the implication only if the customers are made aware of the new technologies and advancements in the banking sector. Therefore, appropriate securities to be implied on the digital methods of banking for reliability and trust of the customers. Objective: In this paper, we formulate a model that represents a means for detecting and describing the transmission of malicious objects through various individual nodes in a server of banking. Method: For a strong banking infrastructure, the challenge is to those concerned with information security to place a monetary value on the protection of information resources. In addition, a trust model for the banking system in online or offline modes is also provided. Results: The results of this model can help in understanding the mechanism by which malicious object spread, to predict the future course of an outbreak and to evaluate the strategies to control. Conclusion: The paper can be concluded to achieve its objective that how to maintain Trust in the banking system in different scenarios along with predicting the outbreak of a perticular malicious object.

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Accurate, fast, and automatic detection and classification of animal images is challenging, but it is much needed for many real-life applications. This paper presents a hybrid model of Mamdani Type-2 fuzzy rules and convolutional neural networks (CNNs) applied to identify and distinguish various animals using different datasets consisting of about 27,307 images. The proposed system utilizes fuzzy rules to detect the image and then apply the CNN model for the object’s predicate category. The CNN model was trained and tested based on more than 21,846 pictures of animals. The experiments’ results of the proposed method offered high speed and efficiency, which could be a prominent aspect in designing image-processing systems based on Type 2 fuzzy rules characterization for identifying fixed and moving images. The proposed fuzzy method obtained an accuracy rate for identifying and recognizing moving objects of 98% and a mean square error of 0.1183464 less than other studies. It also achieved a very high rate of correctly predicting malicious objects equal to recall = 0.98121 and a precision rate of 1. The test’s accuracy was evaluated using the F1 Score, which obtained a high percentage of 0.99052.

A method for detecting false positives in procedure of malware analysis

The paper discusses the possibility of determining false positive by the clustering method. A model of malicious software based on the “behavioral” attribute of malicious objects is described in the paper. Described is a method for studying a sample of malicious objects using a clustering algorithm based on spatial density for applications with noises - DBScan.

An adaptive trust model based on recommendation filtering algorithm for the Internet of Things systems

The Internet of Things (IoT) is growing rapidly and brings great convenience to humans. But it also causes some security issues which may have negative impacts on humans. Trust management is an effective method to solve these problems by establishing trust relationships among interconnected IoT objects. In this paper, we propose an adaptive trust model based on recommendation filtering algorithm for the IoT systems. The utilization of sliding window and time decay function when calculating direct trust can greatly accelerate the convergence rate of trust evaluation.We design a recommendation filtering algorithm to effectively filter out bad recommendations and minimize the impact of malicious objects. An adaptive weight is developed to better combine direct trust and recommendation trust into synthesis trust so as to adapt to the dynamically hostile environment. In the simulation experiments, we compare our adaptive trust model with three related models: TBSM, NRB and NTM. The experimental results indicate that our trust model converges fast and the mean absolute error is always less than 0.05 when the proportion of malicious nodes is from 10% to 70%. The comparative experiments further verify the effectiveness of our trust model in terms of accuracy, convergence rate and resistance to trust related attacks.

Vulnerabilities and countermeasures in electrical substations

The impending and continued threat of cyberattacks on modern utility grids has called for action from the different stakeholders of the electricity sector. This calls for a thorough investigation and review of the weaknesses present in the distribution substations – the backbone of the grid – that can attract attackers to achieve their malicious objectives. The present survey deals with this issue and identifies both the common and specific vulnerabilities present in substations that can be exploited by potential attackers. This work approaches the topic, for the first time, from an attacker's perspective, in order to categorize the possible attack vectors that could be used to first access the substation network, and then disrupt the substation operations under the purview of IEC standards. The reported literature in the field was critically analyzed from an attacker's perspective to highlight the potential threats that can become a liability in cyberattacks on substations. Countermeasures pertaining to these cyberattacks are then detailed and the main elements required for a comprehensive electrical substation cybersecurity solution are finally outlined.

Preventing Computer Virus Prevalence using Epidemiological Modeling and Optimal Control

Computer viruses are a serious threat to the general society, due to their implications for private life and corporative systems. This paper begins to briefly illustrate the dynamics of computer viruses within a network system, by taking advantage of the EpiModel R package and using a SIR (Susceptible–Infected–Recovered) epidemic model. However, since devices are not constantly immune to cyberattacks, a SIRS model with an optimal control application is proposed to minimize the levels of infections caused by malicious objects. Additionally, real numerical data related to the number of reported cybercrimes in Japan from 2012 to 2017 are considered. The existence and uniqueness of an optimal control for the proposed control problem are proved. Under proper investment costs, numerical simulations in Matlab show the effectiveness of the proposed control strategy in increasing the rate of immunity and decreasing the chances of re–susceptibility to cyberattacks.

Discrimination-aware trust management for social internet of things

Internet of Things combined with social networks, has emerged as an interesting research area which is referred to as Social Internet of Things (SIoT). Objects in SIoT interact with each other based on their social behavior. In this network, any object can be a service provider or a service consumer. Social objects are expected to be able to easily discover their desired services in a trusted way. Those that belong to humans are usually selfish. Discriminative objects are the ones that do not contribute to providing satisfactory services in some circumstances. By considering discriminative behavior as rational behavior, we introduce a discriminative-aware trust management (DATM) system for service provisioning in SIoT. DATM employs the ratings of objects and is based on a data mining model that compares the context of service query with the contexts of other raters’ previous queries. It takes metrics such as social similarity, importance of the service, and provider's remaining energy into account and takes the problem to a three-dimensional space where weighted-kNN is used to weigh the contribution of each of the k previous experiences in the estimation of trust value. Simulations, in the presence of discriminative and malicious objects, demonstrate that DATM can well detect objects’ selfish behaviors compared to other approaches which ignore social relationships or discrimination in the calculation of trust. Moreover, our scheme resists trust related attacks and does not allow malicious objects to damage the system.

Attacking Key Management in Ransomware

Ransomware have observed a steady growth over the years with several concerning trends that indicate efficient, targeted attacks against organizations and individuals alike. These opportunistic attackers indiscriminately target both public and private sector entities to maximize gain. In this article, we highlight the criticality of key management in ransomware's cryptosystem in order to facilitate building effective solutions against this threat. We introduce the ransomware kill chain to elucidate the path our adversaries must take to attain their malicious objective. We examine current solutions presented against ransomware in light of this kill chain and specify which constraints on ransomware are being violated by the existing solutions. Finally, we present the notion of memory attacks against ransomware's key management and present our initial experiments with dynamically extracting decryption keys from real-world ransomware. Results of our preliminary research are promising and the extracted keys were successfully deployed in subsequent data decryption.