Dr Mohammad Shan-A-Khuda

Sound classification is a multifaceted task that necessitates the gathering and processing of vast quantities of data, as well as the construction of machine learning models that can accurately distinguish between various sounds. In our project, we implemented a novel methodology for classifying both musical instruments and environmental sounds, utilizing convolutional and recurrent neural networks. We used the Mel Frequency Cepstral Coefficient (MFCC) method to extract features from audio, which emulates the human auditory system and produces highly distinct features. Knowing how important data processing is, we implemented distinctive approaches, including a range of data augmentation and cleaning techniques, to achieve an optimized solution. The outcomes were noteworthy, as both the convolutional and recurrent neural network models achieved a commendable level of accuracy. As machine learning and deep learning continue to revolutionize image classification, it is high time to explore the development of adaptable models for audio classification. Despite the challenges associated with a small dataset, we successfully crafted our models using convolutional and recurrent neural networks. Overall, our strategy for sound classification bears significant implications for diverse domains, encompassing speech recognition, music production, and healthcare. We hold the belief that with further research and progress, our work can pave the way for breakthroughs in audio data classification and analysis.

Numerous factors such as sociodemographic characteristics contribute to cybercrime victimisation. Previous research suggests that neighbourhood plays a role in cybercrime perpetration. However, despite the theoretical importance and particular interest to law enforcement agencies and policymakers, local area variations in cybercrime victimisation have rarely been examined. Drawing on data from recorded cybercrime incidents within one of the largest police forces in England from a three-year period with a victim dataset of 5,270 individuals enhanced by the Census data, this research untangles the relationships between demographics of cybercrime victims and their resident area characteristics. The research considers four types of cybercrime victimisation: ‘Harassment/Unwanted Contact’, ‘Fraud/Theft/Handling’, ‘Sexual/Indecent Images’ and ‘other types of cybercrime’ (classifications used by the participating police force). Latent Class Analysis (LCA) was applied to rigorously analyse the relationship among the four different types of cybercrime victimisation with victim demographics and resident area-level characteristics. This research finds that each type of cybercrime yielded statistically distinct victim profiles. Vulnerabilities to cybercrime varied among male and female of different age groups, and importantly, the types of residential areas of the victims. Specifically, it is evident that females were much more likely to become cybercrime victims than males for two types of cybercrime: ‘Harassment/Unwanted Contact’, and ‘Sexual/Indecent Images’. Vulnerabilities associated with these two types of cybercrime decreased with the increase of age. Cybercrime victims of ‘Sexual/Indecent Images’ were likely to be 5-14 year-olds living in areas with a higher number of Level 2, Level 4 qualifications and full-time students. Both males and females were vulnerable to ‘Fraud/Theft/Handling’ cybercrime and their resident areas had a higher number of full-time students, Level 4 qualifications and Asians. Finally, victims of ‘other types of cybercrime’ were most likely to be male and their resident areas had a high number of Asians and full-time students. Our work demonstrates that it is possible to apply statistical analysis to routinely collected police data to gain insight into the cybercrime victimisation that occurs across crime types in relation to demographics and area-level variations. These results provide valuable insights into policing cybercrime in England and beyond.

Cybercrime presents numerous issues for police organizations. A key challenge is to understand how best to impart relevant skills and knowledge about cybercrime throughout the organization to enable police officers to react appropriately to such incidents. This article is drawn from research undertaken as part of the CARI Project, a major study into the effectiveness of cybercrime investigation within a large UK police force funded by the Police Knowledge Fund. As part of the needs assessment for the above project, concerns were raised about the effectiveness of existing training arrangements in facilitating the development of cyber skills within police officers. The present research, based on survey data, explored the effectiveness of different training styles as perceived by those who had undertaken cyber training. The research found that officers perceived some modes of training as more effective than others and highlighted some of the organizational contexts that impact negatively on the delivery of effective cyber training. The findings are presented within a context, informed by existing literature, that acknowledges wider debates surrounding the pedagogy of police learning and the organizational challenges of developing cyber skills within police officers. The authors believe that the findings will have relevance to police training policy both in the UK and in the wider international context.

Computer security students benefit from hands-on experience applying security tools and techniques to attack and defend vulnerable systems. Virtual machines (VMs) provide an effective way of sharing targets for hacking. However, developing these hacking challenges is time consuming, and once created, essentially static. That is, once the challenge has been "solved" there is no remaining challenge for the student, and if the challenge is created for a competition or assessment, the challenge cannot be reused without risking plagiarism, and collusion. Security Scenario Generator (SecGen) can build complex VMs based on randomised scenarios, with a number of diverse use-cases, including: building networks of VMs with randomised services and in-thewild vulnerabilities and with themed content, which can form the basis of penetration testing activities; VMs for educational lab use; and VMs with randomised CTF challenges. SecGen has a modular architecture which can dynamically generate challenges by nesting modules, and a hints generation system, which is designed to provide scaffolding for novice security students to make progress on complex challenges. SecGen has been used for teaching at universities, and hosting a recent UK-wide CTF event.

Cybercrime has recently surpassed, in terms of volume, all other forms of crime in the United Kingdom, and has been acknowledged as a national priority. The purpose of this research is to analyse the police cyber-investigation lifecycle: from the experience of the public when reporting cybercrime to call takers, through to the attending officers, officer(s) in charge, and the many units and roles involved in supporting cybercrime investigations. A large scale needs assessment was conducted within one of the largest police forces in England and Wales, involving focus groups and interviews with police staff and strategic leads across key units and roles. The results of the needs assessment document the state of policing cybercrime in a UK police force, along with the improvements and needs that exist across the force and in specific units and roles. In total, 125 needs were identified and further coded based on a thematic analysis. Common themes identified include: knowledge/training, communication, recording, software, roles, governance, procedures, resources, consistency, staffing, national input, face-to-face, interactions with the public, new capabilities, and triage. The most common needs were related to training and knowledge, communications, quality of recording, software, governance, procedures, resourcing, and national input. Due to the nature of the findings, it is likely that some of these identified areas may parallel other police organisations’ experiences at national and international levels.

Cybercrime has recently surpassed, in terms of volume, all other forms of crime in the United Kingdom, and has been acknowledged as a national priority. The purpose of this research is to analyse the police cybcr-invcstigation lifccyclc: from the experience of the public when reporting cybercrime to call takers, through to the attending officers, ofEcer(s) in charge, and the many units and roles involved in supporting cybercrime investigations. A large-scale needs assessment was conducted within one of the largest police forces in-England and Wales, involving focus groups and interviews with police staff and strategic leads across key units and roles. The results of the needs assessment document the state of policing cybercrime in a UK police force, along with the improvements and needs that exist across the force and in specific units and roles. In total, 125 needs were identified and further coded based on a thematic analysis. Due to the nature of the findings, it is likely that some of these identified areas may parallel other police organisations' experiences at national and international levels.

Cybercrime has become one of the most pressing developments for police organisations to engage with over recent years. One of the key challenges here is to understand how best to effectively impart relevant skills and knowledge about cybercrime throughout the organisation to enable police officers to react appropriately to such illicit behaviours. This paper is drawn from mixed-methods research undertaken as part of a major study into the effectiveness of cybercrime investigation within a large UK police force funded by College of Policing/Hefce. The research found that officers perceived some modes of training as considerably more effective than others and, similarly, highlighted some of the organisational contexts that impact negatively on the delivery of effective cyber training to police officers. The authors believe that the findings will have relevance to police training policies both in the UK and in the wider international context.