Crime prediction and monitoring in Porto, Portugal, using machine learning, spatial and text analytics

By Saraiva et al., 2019

Abstract:

Crimes are a common societal concern impacting quality of life and economic growth. Despite the global decrease in crime statistics, specific types of crime and feelings of insecurity, have often increased, leading safety and security agencies with the need to apply novel approaches and advanced systems to better predict and prevent occurrences. The use of geospatial technologies, combined with data mining and machine learning techniques allows for significant advances in the criminology of place. In this study, official police data from Porto, in Portugal, between 2016 and 2018, was georeferenced and treated using spatial analysis methods, which allowed the identification of spatial patterns and relevant hotspots. Then, machine learning processes were applied for space-time pattern mining. Using lasso regression analysis, significance for crime variables were found, with random forest and decision tree supporting the important variable selection. Lastly, tweets related to insecurity were collected and topic modeling and sentiment analysis was performed. Together, these methods assist interpretation of patterns, prediction and ultimately, performance of both police and planning professionals.

Reference:

Saraiva, M., Matijošaitienė, I., Mishra, S., & Amante, A. (2022). Crime prediction and monitoring in porto, portugal, using machine learning, spatial and text analytics. ISPRS International Journal of Geo-Information, 11(7), 400.

Developing machine learning based predictive models for smart policing

By Elluri et al., 2019

Abstract:

Crimes are problematic where normal social issues are confronted and influence personal satisfaction, financial development, and quality-of-life of region. There has been a surge in the crime rate over the past couple of years. To reduce the offense rate, law enforcement needs to embrace innovative preventive technological measures. Accurate crime forecasts help to decrease the crime rate. However, predicting criminal activities is difficult due to the high complexity associated with modeling numerous intricate elements. In this work, we employ statistical analysis methods and machine learning models for predicting different types of crimes in New York City, based on 2018 crime datasets. We combine weather, and its temporal attributes like cloud cover, lighting and time of day to identify relevance to crime data. We note that weather related attributes play a negligible role in crime forecasting. We have evaluated the various the consideration of weather datasets, on different types of crime committed. Our proposed methodology will enable law enforcement to make effective decisions on appropriate resource allocation, including backup officers related to crime type and location.

Reference:

Elluri, L., Mandalapu, V., & Roy, N. (2019, June). Developing machine learning based predictive models for smart policing. In 2019 IEEE International Conference on Smart Computing (SMARTCOMP) (pp. 198-204). IEEE.

Forecasting identity theft victims: Analyzing characteristics and preventive actions through machine learning approaches

By Hu et al., 2020

Abstract:

Researchers in criminology and criminal justice have been making increasing use of the machine learning approach to investigate questions involving large amounts of digital data. We make use here of survey data on over 220,000 respondents drawn from three waves of the National Crime Victimization Survey Identity Theft Supplement (NCVS-ITS) conducted by the Bureau of Justice Statistics (BJS) in 2012, 2014, and in 2016. We use three distinct machine learning algorithms to analyze these data: 1) logistic regression; 2) decision thee; and, 3) random forest. We assess the efficacy of these approaches against these evaluative criteria: the overall percentage of correct classification, receiver operating characteristics (ROC), the area under the ROC curve (AUC), and feature criticality. Our findings indicate that the logistic regression algorithm performs best in predicting overall identity theft victimization, misuse of credit cards, misuse of financial accounts of other types, and the opening of new accounts; the random forest algorithm performs best in predicting misuse of checking/saving accounts. Our findings suggest that the respondent's age, educational level, and online shopping frequency are significantly related to identity theft victimization. Additionally, frequently checking credit reports and changing passwords of financial accounts are strong predictors of identity theft victimization. We draw out the implications of our work for our collective understanding of identity theft, and for informing our judgement as to the potential utility of the use of machine learning approaches in criminology and criminal justice.

Reference:

Hu, X., Zhang, X., & Lovrich, N. P. (2022). Forecasting identity theft victims: Analyzing characteristics and preventive actions through machine learning approaches. In The New Technology of Financial Crime (pp. 183-212). Routledge.

Robot-Based Security Management System for Smart Cities Using Machine Learning Techniques

By AIHamad et al., 2023

Abstract:

Recently, smart cities are developing more slowly, gathering plenty of data and communication skills to improve service worth. Despite the smart city concept offerings many beneficial services, security management is still a significant problem because of shared threats and activities. The security aspects of smart cities should be constantly assessed to remove the unnecessary events employed to improve the superiority of the facilities to solve the issues. This study shows how robots are used in the smart city to manage privacy-related problems and actively learn how to forecast the superiority of facilities. Today, smart city development depends heavily on advancing technologies like the Internet of Things (IoT), Artificial Intelligence (AI), Blockchain, and Geospatial Technology. Machine learning, a branch of artificial intelligence, excels in security management systems. The proposed model may overwhelm the security challenges and presents how to keep and obtain their necessary robot-based security solutions by providing maintaining security services.

Reference:

AlHamad, A. Q. M., Hamadneh, S., Nuseir, M. T., Alshurideh, M. T., Alzoubi, H. M., & Al Kurdi, B. (2024). Robot-Based Security Management System for Smart Cities Using Machine Learning Techniques. In Cyber Security Impact on Digitalization and Business Intelligence: Big Cyber Security for Information Management: Opportunities and Challenges (pp. 169-180). Cham: Springer International Publishing.

Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, applications, challenges and future research directions

By Habbal et al., 2023

Abstract:

Artificial Intelligence (AI) has become pervasive, enabling transformative advancements in various industries including smart city, smart healthcare, smart manufacturing, smart virtual world and the Metaverse. However, concerns related to risk, trust, and security are emerging with the increasing reliance on AI systems. One of the most beneficial and original solutions for ensuring the reliability and trustworthiness of AI systems is AI Trust, Risk and Security Management (AI TRiSM) framework. Despite being comparatively new to the market, the framework has demonstrated already its effectiveness in various products and AI models. It has successfully contributed to fostering innovation, building trust, and creating value for businesses and society. Due to the lack of systematic investigations in AI TRiSM, we carried out a comprehensive and detailed review to bridge the existing knowledge gaps and provide a better understanding of the framework from both theoretical and technical standpoints. This paper explores various applications of the AI TRiSM framework across different domains, including finance, healthcare, and the Metaverse. Futhermore, the paper discusses the obstacles related to implementing AI TRiSM framework, including adversarial attacks, the constantly changing landscape of threats, ensuring regulatory compliance, addressing skill gaps, and acquiring expertise in the field. Finally, it explores the future directions of AI TRiSM, emphasizing the importance of continual adaptation and collaboration among stakeholders to address emerging risks and promote ethical and enhanced overall security bearing for AI systems.

Reference:

Habbal, A., Ali, M. K., & Abuzaraida, M. A. (2024). Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, applications, challenges and future research directions. Expert Systems with Applications, 240, 122442.

Intelligent Resource Allocation and Optimization for Industrial Robotics Using AI and Blockchain

By Vashishth et al., 2023

Abstract:

This chapter focuses on the application of intelligent resource allocation and optimization techniques for industrial robotics systems using the synergistic integration of artificial intelligence (AI) and blockchain technologies. Efficient resource allocation is crucial for maximizing the performance and productivity of industrial robotics, and AI-based approaches offer the ability to dynamically allocate resources based on real-time data and system requirements. Additionally, blockchain technology provides a decentralized and secure platform for recording and verifying resource allocation transactions, ensuring transparency and trust in the allocation process. The chapter explores various AI algorithms and models that can be employed for resource allocation and optimization in industrial robotics, including machine learning, evolutionary algorithms, and reinforcement learning. Furthermore, the chapter investigates how blockchain technology can enhance resource allocation and optimization by providing a distributed ledger for recording and verifying resource transactions.

Reference:

Vashishth, T. K., Sharma, V., Sharma, K. K., Kumar, B., Chaudhary, S., & Panwar, R. (2024). Intelligent Resource Allocation and Optimization for Industrial Robotics Using AI and Blockchain. In AI and Blockchain Applications in Industrial Robotics (pp. 82-110). IGI Global.

The Expanding Role of Artificial Intelligence in Collaborative Robots for Industrial Applications: A Systematic Review of Recent Works

By Borboni et al., 2023

Abstract:

A collaborative robot, or cobot, enables users to work closely with it through direct communication without the use of traditional barricades. Cobots eliminate the gap that has historically existed between industrial robots and humans while they work within fences. Cobots can be used for a variety of tasks, from communication robots in public areas and logistic or supply chain robots that move materials inside a building, to articulated or industrial robots that assist in automating tasks which are not ergonomically sound, such as assisting individuals in carrying large parts, or assembly lines. Human faith in collaboration has increased through human–robot collaboration applications built with dependability and safety in mind, which also enhances employee performance and working circumstances. Artificial intelligence and cobots are becoming more accessible due to advanced technology and new processor generations. Cobots are now being changed from science fiction to science through machine learning. They can quickly respond to change, decrease expenses, and enhance user experience. In order to identify the existing and potential expanding role of artificial intelligence in cobots for industrial applications, this paper provides a systematic literature review of the latest research publications between 2018 and 2022. It concludes by discussing various difficulties in current industrial collaborative robots and provides direction for future research.

Reference:

Borboni, A., Reddy, K. V. V., Elamvazuthi, I., AL-Quraishi, M. S., Natarajan, E., & Azhar Ali, S. S. (2023). The Expanding Role of Artificial Intelligence in Collaborative Robots for Industrial Applications: A Systematic Review of Recent Works. Machines, 11(1), 111.

Artificial Intelligence-Based Cyber Security in the Context of Industry 4.0—A Survey

By de Azambuja et al., 2023

Abstract:

The increase in cyber-attacks impacts the performance of organizations in the industrial sector, exploiting the vulnerabilities of networked machines. The increasing digitization and technologies present in the context of Industry 4.0 have led to a rise in investments in innovation and automation. However, there are risks associated with this digital transformation, particularly regarding cyber security. Targeted cyber-attacks are constantly changing and improving their attack strategies, with a focus on applying artificial intelligence in the execution process. Artificial Intelligence-based cyber-attacks can be used in conjunction with conventional technologies, generating exponential damage in organizations in Industry 4.0. The increasing reliance on networked information technology has increased the cyber-attack surface. In this sense, studies aiming at understanding the actions of cyber criminals, to develop knowledge for cyber security measures, are essential. This paper presents a systematic literature research to identify publications of artificial intelligence-based cyber-attacks and to analyze them for deriving cyber security measures. The goal of this study is to make use of literature analysis to explore the impact of this new threat, aiming to provide the research community with insights to develop defenses against potential future threats. The results can be used to guide the analysis of cyber-attacks supported by artificial intelligence.

Reference:

de Azambuja, A. J. G., Plesker, C., Schützer, K., Anderl, R., Schleich, B., & Almeida, V. R. (2023). Artificial Intelligence-Based Cyber Security in the Context of Industry 4.0—A Survey. Electronics, 12(8), 1920.

Enhancing Industrial Robotics Performance and Security With AI and Blockchain Technologies

By Varadam et al., 2023

Abstract:

Industrial robotics are becoming more widely used, but their performance and security must be urgently enhanced to satisfy the needs of contemporary industrial contexts. This chapter focuses on how AI and blockchain technology might improve industrial robotic systems' performance while guaranteeing strong security precautions. The capabilities of industrial robots are greatly enhanced by AI technologies. Robots may improve their performance, gain new abilities, and adapt to changing circumstances by utilising cutting-edge machine learning techniques. Robots may learn from their experiences thanks to the incorporation of AI, which improves their operational effectiveness, precision, and decision-making abilities. AI enables robots to optimise their performance, spot anomalies, and proactively resolve potential difficulties, resulting in increased production and less downtime. This is done through real-time data analysis and predictive analytics. Incorporating blockchain technology also provides an industrial robotics system with a safe and open framework.

Reference:

Varadam, D., Shankar, S. P., Bharadwaj, A., Saxena, T., Agrawal, S., & Dayananda, S. (2024). Enhancing Industrial Robotics Performance and Security With AI and Blockchain Technologies. In AI and Blockchain Applications in Industrial Robotics (pp. 58-81). IGI Global.

MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots

By Deng et al., 2023

Abstract:

Large language models (LLMs), such as chatbots, have made significant strides in various fields but remain vulnerable to jailbreak attacks, which aim to elicit inappropriate responses. Despite efforts to identify these weaknesses, current strategies are ineffective against mainstream LLM chatbots, mainly due to undisclosed defensive measures by service providers. Our paper introduces MASTERKEY, a framework exploring the dynamics of jailbreak attacks and countermeasures. We present a novel method based on time-based characteristics to dissect LLM chatbot defenses. This technique, inspired by time-based SQL injection, uncovers the workings of these defenses and demonstrates a proof-of-concept attack on several LLM chatbots. Additionally, MASTERKEY features an innovative approach for automatically generating jailbreak prompts that target well-defended LLM chatbots. By fine-tuning an LLM with jailbreak prompts, we create attacks with a 21.58% success rate, significantly higher than the 7.33% achieved by existing methods. We have informed service providers of these findings, highlighting the urgent need for stronger defenses. This work not only reveals vulnerabilities in LLMs but also underscores the importance of robust defenses against such attacks.

Reference:

Deng, G., Liu, Y., Li, Y., Wang, K., Zhang, Y., Li, Z., ... & Liu, Y. MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots.

Strategically constructed narratives on artificial intelligence: What stories are told in governmental artificial intelligence policies?

By AA Guenduez, T Mettler - Government Information Quaterly, 2023 - Elsevier

Abstract:

What stories are told in national artificial intelligence (AI) policies? Combining the novel technique of structural topic modeling (STM) and qualitative narrative analysis, this paper examines the policy narratives in 33 countries’ AI policies. We uncover six common narratives that are dominating the political agenda concerning AI. Our findings show that the policy narratives' saliences vary across time and countries. We make several contributions. First, our narratives describe well-grounded, supportable conceptions of AI among governments, and show that AI is still a fairly novel, multilayered, and controversial phenomenon. Building on the premise that human sense making is best represented and supported by narration, we address the applied rhetoric of governments to either minimize the risks or exalt the opportunities of AI. Second, we uncover the four prominent roles governments seek to take concerning AI implementation: enabler, leader, regulator, and/or user. Third, we make a methodological contribution toward data-driven, computationally-intensive theory development. Our methodological approach and the identified narratives present key starting points for further research.

Reference:

Guenduez, A. A., & Mettler, T. (2023). Strategically constructed narratives on artificial intelligence: What stories are told in governmental artificial intelligence policies?. Government Information Quarterly, 40(1), 101719.

Artificial Intelligence (AI) bot ChatGPT in higher education and cyber-situational crime prevention (Cyber-SCP) strategy

Sinchul Back, Ph.D.

President & CEO, the Royal Robotics & AI Security

Assistant Professor, the University of Scranton

Abstract:

As Artificial Intelligence (AI) systems continue to evolve and expand, their impact on academia has been a topic of growing concern in recent years. OpenAI’s free tool ChatGPT recently released has been shown to generate decent quality academic essays at schools and colleges. This innovative technology is now available to all users for free, making it a major threat to the integrity our education systems hold. The purpose of this study is to assess current plagiarism detection systems and AI chatbot generated artifacts through a cyber-situational crime prevention (Cyber-SCP) theoretical framework. This research investigated short essays provided by college students and derived from ChatGPT platform in order to point out whether these detection systems were effectively to distinguish the originality of the short essays. In this regard, to evaluate the originality of contents for all students-provided and ChatGPT-generated essays, we employed AI output detector and existing plagiarism detector(s). The findings of this study indicate that ChatGPT could provide content on diverse topics with high originality. In addition, most generated essays were detected using the AI output detector. Policy implications are discussed.

How Law Enforcement Utilizes AI to Deal with Crime

Sinchul Back, Ph.D.

President & CEO, the Royal Robotics & AI Security

Assistant Professor, the University of Scranton

Abstract:

Due to the advancement of Artificial Intelligence (AI), all sectors of society have been affected by AI. AI has been beneficial from public sector to private sector; however, criminals have also taken advantage of the new technology to conduct malicious activities, expand existing vulnerabilities, and introduce new threats. This article explores the malicious uses of AI capabilities. The purpose of this study is to articulate the types of activities and corresponding risks of using AI. Accordingly, this study will discuss the current use of AI in the criminal justice system to fight against the malicious use of AI. Finally, this study suggests a road map for government officials to effectively combat criminal use of AI by using strategic policies.