1393 research outputs found
Sort by
Enhancing Real-Time Streaming Content Security: An Adaptive QIM Watermarking Approach for Dynamic Tampering Detection
No full textThe legitimacy and integrity of live-streaming content remain a concern. According to studies, conventional watermarking solutions still need to manage the dynamic nature of streaming content. In this paper, we assess the restrictions of existing techniques and offer an adaptive quantitative index modulation (QIM) watermarking solution. Historical approaches struggled with dynamic frame rates, resolution changes, and real-time processing, resulting in insufficient tampering detection. The artifact uses adaptive Quantization Index Modulation (QIM) to distinguish itself in real-time streaming. The artifact detects manipulation via temporal discrepancies, content updates, and latency limits. This design research seeks a new watermarking solution. A comprehensive solution for ensuring authenticity, unaltered state, and reliable delivery of real-time streaming content is proposed. It stands out due to its adaptability to streaming media dynamics
Test Suite Optimization Using Machine Learning Techniques: A Comprehensive Study
Get PDFSoftware testing is an essential yet costly phase of the software development lifecycle. While machine learning-based test suite optimization techniques have shown promise in reducing testing costs and improving fault detection, a comprehensive evaluation of their effectiveness across different environments is still lacking. This paper reviews 43 studies published between 2018 and 2023, covering various test case selection, prioritization, and reduction techniques using machine learning. The findings reveal that conventional machine learning techniques, particularly supervised learning methods, have been widely adopted for test case prioritization and selection. Recent advancements, such as deep learning and hybrid models, show potential in improving fault detection rates and scalability, though challenges remain in adapting these techniques to large-scale and dynamic environments. Additionally, Generative AI and large language models (LLMs) are emerging as promising tools for automating aspects of test case generation and prioritization, offering new avenues for future research in enhancing test suite optimization. The study identifies recent trends, challenges, and opportunities for further research, with a focus on both conventional and emerging methods, including deep learning, hybrid approaches, and Generative AI models. By systematically analyzing these techniques, this work contributes to the understanding of how machine learning and Generative AI can enhance test suite optimization and highlights future directions for improving the scalability and real-world applicability of these methods
An Exploration of Machine Learning Security
Get PDFInnovations in the fields of computer science and mathematics have enabled machines to learn incredibly complicated patterns and abstractions without explicit tutoring. Unfortunately, threats have been developed targeting machine learning systems that may affect large groups of individuals including model producers and maintainers, model users, and individuals who may be implicitly or explicitly represented by the information used by the model. Consequently, it is crucial to understand possible attacks that may be employed on machine learning models at the algorithmic level for better mitigation strategies. This research seeks to work towards a better understanding of vulnerabilities that exist in the space of machine learning in three important segments. First, as a tool to aid in interpreting attacks to benefit possible defensive mechanisms in the future, a taxonomy and threat model are created that highlight possible similarities and differences between existing attacks. Next, a novel exploitative attack is developed that aims to generate evasion samples on tree-based models, including both single and ensemble classifiers. Lastly, a novel exploratory attack is developed that aims to extract representative information from the training datasets of hypersphere-based models as well as learned parameters of the victim models themselves. The proposed taxonomy is based on a review of current literature surrounding the union of cybersecurity and machine learning. Future attacks may supersede the identified relationships found in this study, so the taxonomy itself serves as a stepping-stone for future work to enhance. To evaluate the proposed attacks, a series of victim models were fitted on a variety of datasets to exhibit their data agnostic properties. After the attacks have taken place, multiple metrics have been used to illustrate their effectiveness. Additionally, this research discusses possible uses of the developed attack algorithms in the machine learning paradigm
Transforming Information Systems Management: A Reference Model for Digital Engineering Integration
No full textDigital engineering practices offer significant yet underutilized potential for improving information assurance and system lifecycle management. This paper examines how capabilities like model-based engineering, digital threads, and integrated product lifecycles can address gaps in prevailing frameworks. A reference model demonstrates applying digital engineering techniques to a reference information system, exhibiting enhanced traceability, risk visibility, accuracy, and integration. The model links strategic needs to requirements and architecture while reusing authoritative elements across views. Analysis of the model shows digital engineering closes gaps in compliance, monitoring, change management, and risk assessment. Findings indicate purposeful digital engineering adoption could transform cybersecurity, operations, service delivery, and system governance through comprehensive digital system representations. This research provides a foundation for maturing application of digital engineering for information systems as organizations modernize infrastructure and pursue digital transformation
CyberEducation-By-Design™: Developing A Framework for Cybersecurity Education at Secondary Education Institutions in Arizona
Get PDFMost survey results agree that there is a current and ongoing shortage of skilled cybersecurity workers that places our privacy, infrastructure, and nation at risk. Estimates for the global Cybersecurity Workforce Gap range from 2.72 million (ISC2, 2021) to 3.5 million (Cyber Academy, 2021) for 2021 and the United States estimates range from 465,000 (Brooks, 2021) to over 769,000 (Cyber Seek, 2022) open jobs as of November 2022. The most optimistic estimates still demonstrate a critical issue. As cybersecurity threats continue to grow in sophistication, scope, and scale, the ability to secure the United States from these threats lies in the ability to develop cybersecurity professionals with the knowledge, skills, and abilities (KSAs) to accomplish the tasks associated with their cyber roles. The ability to supply qualified cybersecurity professionals is outpaced by the growing demand as previously outlined. This study proposes that conducting a case study of existing cybersecurity programs at secondary education institutions can identify the critical elements of these programs. These elements can be codified into program profiles and further refined into a comprehensive cybersecurity education framework for secondary education institutions. This framework can be used by school districts throughout Arizona to develop cybersecurity programs and ultimately develop qualified and competent cybersecurity professionals to overcome the cybersecurity workforce gap
SUTMS - Unified Threat Management Framework for Home Networks
Get PDFHome networks were initially designed for web browsing and non-business critical applications. As infrastructure improved, internet broadband costs decreased, and home internet usage transferred to e-commerce and business-critical applications. Today’s home computers host personnel identifiable information and financial data and act as a bridge to corporate networks via remote access technologies like VPN. The expansion of remote work and the transition to cloud computing have broadened the attack surface for potential threats. Home networks have become the extension of critical networks and services, hackers can get access to corporate data by compromising devices attacked to broad- band routers. All these challenges depict the importance of home-based Unified Threat Management (UTM) systems. There is a need of unified threat management framework that is developed specifically for home and small networks to address emerging security challenges. In this research, the proposed Smart Unified Threat Management (SUTMS) framework serves as a comprehensive solution for implementing home network security, incorporating firewall, anti-bot, intrusion detection, and anomaly detection engines into a unified system. SUTMS is able to provide 99.99% accuracy with 56.83% memory improvements. IPS stands out as the most resource-intensive UTM service, SUTMS successfully reduces the performance overhead of IDS by integrating it with the flow detection mod- ule. The artifact employs flow analysis to identify network anomalies and categorizes encrypted traffic according to its abnormalities. SUTMS can be scaled by introducing optional functions, i.e., routing and smart logging (utilizing Apriori algorithms). The research also tackles one of the limitations identified by SUTMS through the introduction of a second artifact called Secure Centralized Management System (SCMS). SCMS is a lightweight asset management platform with built-in security intelligence that can seamlessly integrate with a cloud for real-time updates
A Framework towards an efficient solution for the transportation of University of Bahrain Students
No full textThis research work is an attempt to develop an efficient solution of the transportation problem of University of Bahrain (UoB) students. The main contribution of this paper is creating a Bahrain map grid of bus stations, generating random requests from riders in any region based on population density, and estimate the number and capacities of buses required. The analysis of territory and population density in the kingdom of Bahrain reveals that riders issue requests from 80 regions distributed over the four governorates. The requests are generated for 15 time slots (3 per day) for the whole semester (15 weeks). Based on the generated requests, the statistics were calculated per time slot for all 15 weeks. The obtained results show that no more than 47 buses (with 50 seats/bus) are needed. The results also shows that each bus will replace 16.5 cars, assuming an average of 3 riders per car. It also reveals that the increasing reliance on students’ private cars has a direct impact on traffic congestion. More efficient bus network and timings will encourage students to use the new bus system
Web Injection and Banking Trojan Malware -A Systematic Literature Review
No full textBanking trojan malware focuses on stealing credentials for financial services. A common technique used to facilitate this theft is web injection. Web injects work by modifying web page code or intercepting user input within a browser. Multiple papers in the literature discuss web injects and banking trojan malware; however, this paper extends the existing literature by answering key questions related to web inject usage in banking trojan malware.Specifically, this paper systematically analyzes the available literature to describe which threat actors use banking trojans, identify the malware families employing web injects, enumerate web injection techniques, and define the victims of banking trojans. To answer these questions, a 3-phase systematic literature review was conducted. In total 258 articles were reviewed and analyzed using a custom classification schema. The analysis revealed that web injects in banking malware trojans are a large threat in the cyber landscape
A Study of Stem and Non-Stem College Students’ Smart TV Attitudes (The Trade-Off Between Functionality and Security/Privacy)
Get PDFInternet-of-Things (IoT) usage surged over the past decade, and its advancement of intricate devices brings obvious convenience to users. IoT devices such as Smart TVs offer services and features that are desirable and favorable to consumers. However, all that convenience comes with security and privacy concerns. Smart TVs have been the target of attacks due to their internet connectivity. Moreover, personally identifiable information (PII), browsing history, and watching preferences, are being collected, leaked, and sold.
Previous research showed that users care that their data is protected but have minimal privacy awareness. Moreover, some researchers claimed that even if consumers were made aware of privacy issues, using the smart TVs’ functionalities took higher precedence than protecting their privacy. This study will extend previous studies and investigate claims that informing users about privacy does not change their attitudes. The aim is to investigate different groups of students at a small mid-western public institution of higher education: across domains, STEM and Non-STEM programs, junior/senior and freshmen/sophomore students’ responses and attitudes will be compared. The research will investigate whether training and exposure to security programs and courses affect students’ security and privacy knowledge, awareness, and attitudes