Cybercrime Detection Research Articles

KEYSTROKE DYNAMICS FEATURES IN FORENSIC IDENTIFICATION:

This article discusses the use of typing dynamics, or individual typing style, as a form of biometric identification. It is found that keystroke dynamics has great forensic identification potential, particularly in the detection and investigation of cybercrimes. The study examines different characteristics of keystroke dynamics, such as key press time and release latency, through an experiment that collects typing data from 9 students. The results suggest that, although keystroke dynamics can be influenced by factors such as keyboard type, a set of typing characteristics can be used to accurately identify individuals, paving the way for advancements in the forensic application of this technology.

The Role and Importance of Digital Forensics and Digital Evidence in Cyber Crime Detection

The Role and Importance of Digital Forensics and Digital Evidence in Cyber Crime Detection

РОЗРОБЛЕННЯ МЕТОДУ ДОСЛІДЖЕННЯ КІБЕРЗЛОЧИНІВ ЗА ТИПОМ ВІРУСІВ-ВИМАГАЧІВ З ВИКОРИСТАННЯМ МОДЕЛЕЙ ШТУЧНОГО ІНТЕЛЕКТУ В СИСТЕМІ МЕНЕДЖМЕНТУ ІНФОРМАЦІЙНОЇ БЕЗПЕКИ КРИТИЧНОЇ ІНФРАСТРУКТУРИ

In this article the authors focused on analyzing the possibilities of using artificial intelligence models for effective detection and analysis of cybercrimes. A comprehensive method using artificial intelligence algorithms such as Random Forest and Isolation Forest algorithms is developed and described to detect ransomware which is one of the main threats to information security management systems (ISMS) in the field of critical infrastructure. The result of the study is the determination of the compatibility of such methods with the requirements of ISO 27001:2022 emphasizing the importance of integrating innovative AI technologies into already existing security systems. In addition the article analyzes the potential advantages of such integration including compliance with the requirements of international information security frameworks. Keywords: Isolation Forest Random Forest critical infrastructure information security management system ISO 27001 cyber security cyber security standard cybercrime ISMS ransomware siem edr security monitoring antivirus machine learning computer networks information systems.

Insights into Cybercrime Detection and Response: A Review of Time Factor

Amidst an unprecedented period of technological progress, incorporating digital platforms into diverse domains of existence has become indispensable, fundamentally altering the operational processes of governments, businesses, and individuals. Nevertheless, the swift process of digitization has concurrently led to the emergence of cybercrime, which takes advantage of weaknesses in interconnected systems. The growing dependence of society on digital communication, commerce, and information sharing has led to the exploitation of these platforms by malicious actors for hacking, identity theft, ransomware, and phishing attacks. With the growing dependence of organizations, businesses, and individuals on digital platforms for information exchange, commerce, and communication, malicious actors have identified the susceptibilities present in these systems and have begun to exploit them. This study examines 28 research papers focusing on intrusion detection systems (IDS), and phishing detection in particular, and how quickly responses and detections in cybersecurity may be made. We investigate various approaches and quantitative measurements to comprehend the link between reaction time and detection time and emphasize the necessity of minimizing both for improved cybersecurity. The research focuses on reducing detection and reaction times, especially for phishing attempts, to improve cybersecurity. In smart grids and automobile control networks, faster attack detection is important, and machine learning can help. It also stresses the necessity to improve protocols to address increasing cyber risks while maintaining scalability, interoperability, and resilience. Although machine-learning-based techniques have the potential for detection precision and reaction speed, obstacles still need to be addressed to attain real-time capabilities and adjust to constantly changing threats. To create effective defensive mechanisms against cyberattacks, future research topics include investigating innovative methodologies, integrating real-time threat intelligence, and encouraging collaboration.

Effect of Cybercrime on the Academic Performance of Students of Tertiary Institutions in Enugu State, Nigeria

The contribution of internet to the development of the nation has been marred by cybercrime activities. Cybercrime is emerging as a very concrete threat, not only in Nigeria but to the entire world. The high level of insecurity on the internet is becoming worrisome so much in the sense that transactions on the internet have become a thing of doubt. This research intends to examine the effect cybercrime has on the academic performance of students of tertiary institutions in Enugu State Nigeria. Survey research method was used in which questionnaire was distributed to various respondents in the execution of the study. The population of the study was 8,034, while the sample size was 381using Taro Yamani statistical formular. Chi-square and simple percentages was used in analyzing data. The study revealed that cybercrime has significant negative effect on study habit, learning outcome and to a large extent was engineered by such factors as uncertainty, and bad leadership. The recommendations suggeststo include into the curriculum of instructions cybercrime asgeneral course to be taught in tertiary institutions. Parents, religious bodies and traditional institutions should aggressively orientate youth on the menace of cybercrime. Creating awareness that hard-work brings prosperity. Meanwhile employment opportunities, empowerment and relief fund for both undergraduates and graduates should also be factored by the Government. Police and othersecurity agencies should be made to undertake courses on cybercrime detection using technology as opposed to the current stop andsearch which is intruding into personal privacy and embarrassing the innocent citizen.

Advanced Cybercrime Detection: A Comprehensive Study on Supervised and Unsupervised Machine Learning Approaches Using Real-world Datasets

In the ever-evolving field of cybersecurity, sophisticated methods—which combine supervised and unsupervised approaches—are used to tackle cybercrime. Strong supervised tools include Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), while well-known unsupervised methods include the K-means clustering model. These techniques are used on the publicly available StatLine dataset from CBS, which is a large dataset that includes the individual attributes of one thousand crime victims. Performance analysis shows the remarkable 91% accuracy of SVM in supervised classification by examining the differences between training and testing data. K-Nearest Neighbors (KNN) models are quite good in the unsupervised arena; their accuracy in detecting criminal activity is impressive, at 79.56%. Strong assessment metrics, such as False Positive (FP), True Negative (TN), False Negative (FN), False Positive (TP), and False Alarm Rate (FAR), Detection Rate (DR), Accuracy (ACC), Recall, Precision, Specificity, Sensitivity, and Fowlkes–Mallow's scores, provide a comprehensive assessment.

Research on Feature Extraction Strategies for Cybercrime Crimes Combined with Deep Learning and Their Probabilistic Models

AbstractIn this paper, in order to improve the accuracy and precision of the detection and identification of cybercrime cases, eliminating the incomplete and ambiguous information obtained from a single source of evidence, combined with the procedural steps of the sampling and forensics for the detection of cybercrime cases, a cybercrime detection and control model based on the fuzzy reasoning and the improvement of the D-S algorithm is proposed. Combined with the application of the improved D-S evidence theory in the fusion of cyber evidence, the weighted Bayes is combined to achieve effective forensics of cybercrime evidence. The improved D-S evidence theory algorithm achieves a detection rate of 0.989 for network anomalous data, which has an obvious advantage in network data fusion over the no-preprocessing, original D-S evidence fusion algorithm. The intrusion path generation algorithm considers the intrusion risk of intrusion path IV5 to be the highest at 0.186 with the intrusion paths <H1, W2, S2, S3, W5, S3, T5>.

The Prevention of Electronic Crimes Act (PECA) 2016 Understanding the Challenges in Pakistan

Cybercrime (e.g., hacking, phishing, and spreading false news) is a criminal activity performed through computing machines. The frequency of these kinds of activities is increasing at a fast pace around the globe and damaging society with financial losses and trust. Miniaturization of computing and the compulsion of web usage in our daily lives are two significant factors that are becoming more pervasive in a rapid increase of cyber security issues, making it a complex problem to tackle. The detection and prevention of cybercrime is paramount for any lawful country. Cybercrime can occur anywhere at any time, and ultimately, the outcome could be devastating. The availability of cyber laws is the first step towards resolving this issue. Still, unfortunately, Pakistani lawmaker institutions, i.e., the National Assembly and Senate of Pakistan, passed the Cybercrime Act very late, i.e., in 2016. Fighting against Cybercrimes in Pakistan is challenging because we still lack a professional workforce and technology. Pakistan is one of the major victims of this problem. This study mainly focuses on the legislation passed by the Government of Pakistan with the Prevention of Electronic Crimes Act, 2016" followed by analyzing these cyber laws in tackling cybercrime cases.

PERAN INTELIJEN KEPOLISIAN SEBAGAI TINDAKAN PREVENTIF DALAM MENANGGULANGI TINDAK PIDANA CYBER CRIME

Police Intelligence is one of the areas within the Indonesian National Police which functions as the eyes and ears of the Police organization in preventing and dealing with cyber crimes. The aim of this research is to analyze the role of Police Intelligence in carrying out early detection of cyber crime and to determine the obstacles faced by Police Intelligence in tackling cyber crime. This research uses an empirical normative research type, using primary data and secondary data. Primary data is obtained directly from research in the field, while secondary data consists of primary legal materials and secondary legal materials. The research results show that the role of intelligence and security in preventing the occurrence of Cyber ​​Crime crimes consists of a normative role and a factual role. The normative role is carried out based on provisions in statutory regulations, where in this case Intelkam plays a role in accordance with statutory regulations related to Cyber ​​Crime crimes. Meanwhile, the factual role is carried out by Police Intelligence and Security in dealing with cyber crimes based on the facts of threats that occur in people's lives. The obstacles faced by Intelkam in preventing cyber crime include human resources and infrastructure.

Evaluation of Various Topological Indices of Flabellum Graphs

Graph theory serves as an engaging arena for the investigation of proof methods within the field of discrete mathematics, and its findings find practical utility in numerous scientific domains. Chemical graph theory is a specialized branch of mathematics that uses graphs to represent and analyze the structure and properties of chemical compounds. Topological indices are mathematical properties of graphs that play a crucial role in chemistry. They provide a unique way to connect the structural characteristics of chemical compounds to their corresponding molecular graphs. The flabellum graph Fn(k,j) is obtained with the help of k≥2 duplicates of the cycle graph Cn with a common vertex (known as, central vertex). Then, in j of these duplicates, additional edges are added, joining the central vertex to all non-adjacent vertices. In this article, we compute different degree-based topological indices for flabellum graphs, including some well known indices, such as the Randić index, the atom bond connectivity index, the geometric–arithmetic index, and the Zagreb indices. This research provides an in-depth examination of these specific indices within the context of flabellum graphs. Moreover, the behavior of these indices is shown graphically, in terms of the parameters j,k, and n. Additionally, we have extended the concept of the first Zagreb index, to address the issue of cybercrime. This application enables us to identify criminals who exhibit higher levels of activity and engagement in multiple criminal activities when compared to their counterparts. Furthermore, we conducted a comprehensive comparative analysis of the first Zagreb index against the closeness centrality measure. This analysis sheds light on the effectiveness and relevance of the topological index in the context of cybercrime detection and network analysis.

Detection of content-based cybercrime in Roman Kashmiri using ensemble learning

Detection of content-based cybercrime in Roman Kashmiri using ensemble learning

Cyber Crime Detection and Prevention Techniques on Cyber Cased Objects Using SVM and Smote

Conventional cybersecurity employs crime prevention mechanisms over distributed networks. This demands crime event management at the network level where Detection and Prevention of cybercrimes is a must. A new Framework IDSEM has been introduced in this paper to handle the contemporary heterogeneous objects in cloud environment. This may aid for deployment of analytical tools over the network. A supervised machine learning algorithm like SVM has been implemented to support IDSEM. A machine learning technique Like SMOTE has been implemented to handle imbalanced classification of the sample data. This approach addresses imbalanced datasets by oversampling the minority classes. This will help to solve Social Engineering Attacks (SEA) like Phishing and Vishing. Classification mechanisms like decision trees and probability functions are used in this context. The IDSEM framework could minimize traffic across the cloud network and detect cybercrimes maximally. When results were compared with existing approaches, the results were found to be good, leading to the development of a unique SMOTE algorithm.

Simple, Fast, and Accurate Cybercrime Detection on E-Government with Elastic Stack SIEM

Increased public activity in cyberspace (Internet) during the Covid-19 pandemic has also increased cybercrime cases with various attack targets, including E-Government services. Cybercrime is hidden and occurs unnoticed in E-Government, so handling it is challenging for all government agencies. The characteristics of E-Government are unique and different from other service systems in general, requiring extra anticipation for the prevention and handling of cybercrime attack threats. This research proposes log and event data analysis to detect cybercrime in e-Government using System Information and Event Management (SIEM). The main contribution of this research is a simple, fast, and accurate cybercrime detection process in the e-Government environment by increasing the level of log and event data analysis with the SIEM approach. SIEM technology based on machine learning and big data is implemented with Elastic Stack. The implemented technique can be used as a mitigation program against cybercrime threats that often attack and target e-Government. With simple, accurate, and fast cybercrime detection, it is expected to improve e-Government security and increase public confidence in public services organized by government agencies.

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

Investigation and detection of cybercrimes has been in the spotlight of cybersecurity research for as long as the topic has existed. Modern methods are required to keep up with the pace of the technology and toolset used to facilitate these crimes. Keystroke-injection attacks have been an issue due to the limitations of hardware and software up until recently. This paper presents comprehensive research on keystroke-injection payload generation that proposes the use of deep learning to bypass the security of keystroke-based authentication systems focusing on both fixed-text and free-text scenarios. In addition, it specifies the potential risks associated with keystroke-injection attacks. To ensure the legitimacy of the investigation, a model is proposed and implemented within this context. The results of the implemented implant model inside the keyboard indicate that deep learning can significantly improve the accuracy of keystroke dynamics recognition as well as help to generate effective payload from a locally collected dataset. The results demonstrate favorable accuracy rates, with reported performance of 93–96% for fixed-text scenarios and 75–92% for free-text. Accuracy across different text scenarios was achieved using a small dataset collected with the proposed implant model. This dataset enabled the generation of synthetic keystrokes directly within a low-computation-power device. This approach offers efficient and almost real-time keystroke replication. The results obtained show that the proposed model is sufficient not only to bypass the fixed-text keystroke dynamics system, but also to remotely control the victim’s device at the appropriate time. However, such a method poses high security risks when deploying adaptive keystroke injection with impersonated payload in real-world scenarios.

Optimized Deep Neuro Fuzzy Network for Cyber Forensic Investigation in Big Data-Based IoT Infrastructures

Forensic skills analysts play an imperative support to practice streaming data generated from the IoT networks. However, these sources pose size limitations that create traffic and increase big data assessment. The obtainable solutions have utilized cybercrime detection techniques based on regular pattern deviation. Here, a generalized model is devised considering the MapReduce as a backbone for detecting the cybercrime. The objective of this model is to present an automatic model, which using the misbehavior in IoT device can be manifested, and as a result the attacks exploiting the susceptibility can be exposed by newly devised automatic model. The simulation of IoT is done such that energy constraints are considered as basic part. The routing is done with fractional gravitational search algorithm to transmit the information amongst the nodes. Apart from this, the MapReduce is adapted for cybercrime detection and is done at base station (BS) considering deep neuro fuzzy network (DNFN) for identifying the malwares.

DEVELOPMENT OF MODERN CYBERCRIME PROFILES

In the modern world, the volume of cybercrime is overgrowing. This is a consequence of the mass automation of various society's spheres. Therefore, there is an urgent problem of timely detection and prevention of cybercrimes, allowing business entities and state authorities to respond quickly to mass threats. Many methods and tools for combating cybercrime are used in practice. Software and cyber-physical complexes based on modern mathematical methods are popular today. Artificial intelligence, neural networks, genetic algorithms, blockchains, robots, etc., have proven to be the most effective. But in our opinion, along with such powerful tools, cybercriminals profiling should also be used.

Киберпространство как место совершения преступлений: современные тенденции, особенности, меры предупреждения

The relevance of this topic is due to the fact that the development of technology, the prevalence of computer technology and the Internet among the population have led to the emergence of a global problem for society – cybercrime. The purpose of this study is to analyze crimes committed in the information and digital space in the Russian Federation and determine preventive measures for various areas of this type of crime. Today, we are not yet talking about the timely universal prevention of cybercrime by law enforcement agencies; we consider it necessary to develop legislative regulation of this area of activity and to ensure the necessary retraining of law enforcement agencies to increase knowledge in the field of prevention, prevention and detection of cybercrimes. The methodology consists of dialectical, structural, formal legal and comparative legal methods, analysis and synthesis. The history and causes of crimes in the cyberspace are analyzed, the features of cyber attacks and cybercrimes in various fields are studied, and preventive measures for the corresponding crime are proposed. It is noted that the legal mechanisms of responsibility for some types of crimes are absent in the legislation due to the constantly changing methods of committing crimes, which also make it difficult for law enforcement agencies to solve them. Their solution is seen in the comprehensive application of preventive measures, timely changes in legislation and regular retraining of law enforcement agencies.

MOBİL KİBER KRİMİNALİSTİKAYA HAZIRLIQ METODOLOGİYALARININ TӘDQİQİ

Mobile cyber forensics serves to recover potential digital evidence from mobile devices using digital forensics. The development and spread of mobile technologies, the need for mobile-based services and new requirements have led to the development and transformation of mobile cyber forensics into an important field. In this article, a component model is proposed to assess the readiness potential of the relevant organizations in the field of mobile cyber forensics for the detection of cybercrimes, collection of evidence, and investigation of criminal cases.

A Deep GCN Approach Based on Multidimensional Projections and Classification to Cybercrime Detection in a True Imbalanced Problem with Semisupervision

A Deep GCN Approach Based on Multidimensional Projections and Classification to Cybercrime Detection in a True Imbalanced Problem with Semisupervision

A robust detection and localization technique for copy-move forgery in digital images

Image forensic analysis becomes a major role in the field of digital image security due to tampering and forgery. The image forgery violates the authenticity and ownership of digital images. Copy-move forgery considers a significant kind of image forensic analysis algorithm. In this kind, the forger copies a part of an original image and then pastes it into the selected position from the same image. The purpose of forgery is to hide or highlight a specific region of the original image. To detect copy-move forgery, there are two traditional techniques: block-based and keypoint-based. The main drawback of the keypoint-based technique is the insufficient features for the small and flat regions, which causes undetected forgery. In contrast, the block-based technique has intensive processing. Therefore, this paper proposes a robust scheme that overcomes the drawbacks of the above techniques and maintains their advantages. This scheme adopts three connected stages, the first detects the initial duplicated regions using the SURF-HOG detector and descriptor. Subsequently, the second stage localizes the primary matched regions by SLIC segmentation and then selects the suspicious neighbor regions to be combined with primary regions to obtain the active regions. In the third stage, the block-based technique adopts overlapping Zernike moments to extract sufficient key points from the produced active regions. In the final stage, the duplicated regions are classified into authentic or forged regions. The proposed scheme provides not only forgery detection but also localization and recognition for the duplicated regions. The experimental results show that the proposed scheme is fast and has high accuracy for forgery detection and localization, at least 93.75, and 7.25 in terms of True Positive and False Positive Rates. Moreover, the scheme has high robustness under various conditions and attacks such as geometric transformation attacks and compound photometric attacks. The proposed scheme can be used in sensitive applications such as cybercrime detection and adopted as evidence in the courts.