EPSRC DTP studentship in Cyber Security Analytics: Machine learning threat detection for low complexity edge deployment: threats, risks and mitigation

物联网/边缘设备的部署在整个社会变得越来越普遍，包括在关键的国家基础设施(例如智能能源)中。这些设备由于其多样性(许多制造商和协议)而容易受到广泛的网络攻击，并且由于有限的计算资源(低处理能力)而缺乏安全机制。虽然最近的进步看到了机器学习被用来保护此类设备免受网络攻击，但由于这些轻量级设备上缺乏计算资源，在设备本身上部署保护模型往往是有限的。这个PHD将基于MITRE ATT&CK对抗性威胁建模框架生成威胁，并为边缘设备社区风险评分产生新的方法-包括关于缓解控制的建议。这些将在东芝位于布里斯托尔的研究实验室的真实世界试验台上进行测试。我们正在寻找一位思想开放、富有创造力的人加入我们的团队，并开发具有工业应用的世界级研究成果。你将加入加的夫大学网络安全分析的ESPRC DTP中心，成为在网络安全背景下学习人工智能的人和算法方面的跨学科学生中的一员。

The deployment of IoT/edge devices is becoming increasing prevalent across society, including in critical national infrastructure (e.g. smart energy). These devices are vulnerable to a wide range of cyber attacks due to their diversity (many manufacturers and protocols) and lack of security mechanisms due to limited compute resource (low processing power). While recent advancements have seen machine learning used to protect such devices from cyber attacks, the deployment of protective models on the devices themselves is often limited due to the lack of compute resource on these lightweight devices.This PhD will generate threats based around the MITRE ATT&CK adversarial threat modelling framework, and produce new methods for edge-device community risk scoring - including suggestions around mitigating controls. These will be tested in a real-world testbed at Toshiba's research labs in Bristol. We are seeking an open minded, creative individual to join the team and develop world class research outcomes with industrial applications. You will join the ESPRC DTP Hub in Cyber Security Analytics at Cardiff University, becoming part of an interdisciplinary cohort of students studying the human and algorithmic aspects of AI in the context of cybersecurity.