Data Privacy Threat Modelling for Autonomous Systems: A Survey From the GDPR's Perspective

Azam, Naila; Michala, Lito; Ansari, Shuja; Truong, Nguyen Binh

doi:10.1109/tbdata.2022.3227336

Cited by 13 publications

(5 citation statements)

References 195 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rapid development and integration of autonomous systems, including autonomous aircraft, in urban environments raise significant ethical, safety, and social concerns. The collection and processing of large amounts of data by autonomous systems have privacyrelated concerns that potentially violate people's privacy rights [41]. Security is also an important aspect, as autonomous systems are vulnerable to cyber-attacks and unauthorized access and require strong security measures to protect against potential threats [42].…”

Section: Discussionmentioning

confidence: 99%

Hybrid Turbo-Shaft Engine Digital Twinning for Autonomous Aircraft via AI and Synthetic Data Generation

Aghazadeh Ardebili,

Ficarella,

Longo

et al. 2023

Aerospace

View full text Add to dashboard Cite

Autonomous aircraft are the key enablers of future urban services, such as postal and transportation systems. Digital twins (DTs) are promising cutting-edge technologies that can transform the future transport ecosystem into an autonomous and resilient system. However, since DT is a data-driven solution based on AI, proper data management is essential in implementing DT as a service (DTaaS). One of the challenges in DT development is the availability of real-life data, particularly for training algorithms and verifying the functionality of DT. The current article focuses on data augmentation through synthetic data generation. This approach can facilitate the development of DT in case the developers do not have enough data to train the machine learning (ML) algorithm. The current twinning approach provides a prospective ideal state of the engine used for proactive monitoring of the engine’s health as an anomaly detection service. In line with the track of unmanned aircraft vehicles (UAVs) for urban air mobility in smart city applications, this paper focuses specifically on the common hybrid turbo-shaft in drones/helicopters. However, there is a significant gap in real-life similar synthetic data generation in the UAV domain literature. Therefore, rolling linear regression and Kalman filter algorithms were implemented on noise-added data, which simulate the data measured from the engine in a real-life operational life cycle. For both thermal and hybrid models, the corresponding DT model has shown high efficiency in noise filtration and a certain amount of predictions with a lower error rate on all engine parameters except the engine torque.

show abstract

Section: Discussionmentioning

confidence: 99%

Hybrid Turbo-Shaft Engine Digital Twinning for Autonomous Aircraft via AI and Synthetic Data Generation

Aghazadeh Ardebili,

Ficarella,

Longo

et al. 2023

Aerospace

View full text Add to dashboard Cite

show abstract

“…Thus, there is an emerging demand for refined privacy modeling and assessment. Privacy Impact Assessment (PIA) has been proposed as a potential solution, which could enhance stakeholder confidence and provide verifiable compliance with modern privacy standards [90,91]. Within the CCAVs and platooning, PIA could be considered to be a central tool for assimilating advanced privacy solutions such as differential privacy, federated learning, and homomorphic encryption; however, this is still in its early developmental phase.…”

Section: Assessing Prioritising and Mitigating Privacy Risksmentioning

confidence: 99%

A Comprehensive Survey of Threats in Platooning—A Cloud-Assisted Connected and Autonomous Vehicle Application

Sheik,

Maple,

Epiphaniou

et al. 2023

Information

View full text Add to dashboard Cite

Cloud-Assisted Connected and Autonomous Vehicles (CCAV) are set to revolutionise road safety, providing substantial societal and economic advantages. However, with the evolution of CCAV technology, security and privacy threats have increased. Although several studies have been published around the threat and risk estimation aspects of CCAV, limited research exists on the security implications and emerging threat landscapes in the CCAV platooning application. We conducted an extensive review and categorisation of real-world security incidents and created an account of 132 threats from scholarly sources and 64 threats from recorded events in practice. Furthermore, we defined thirty-one (31) trust domains and outlined eight (8) unique attack vectors to supplement existing research efforts for the systematic security analysis of such cyberinfrastructures. Using these findings, we create a detailed attack taxonomy to communicate threat-related information in CCAV and platooning applications and highlight emerging challenges and ways to safeguard the broader CCAV systems. This work acts as a roadmap to existing researchers and practitioners advocating for a ‘security and privacy by design’ framework for a dynamically evolving CCAV threat landscape.

show abstract

“…al. [20] provides a privacy perspective for the Threat modeling of autonomous systems. The study identifies gaps from twelve different Threat modeling methodologies with respect to privacy requirements specified in General Data Protection Regulations.…”

Section: Threat Modeling Articlesmentioning

confidence: 99%

A Systematic Evaluation of Artificial Intelligence's Impact on the Landscape of Threat Modeling

Pai,

R.Kunte,

Najee

2023

STAIQC

View full text Add to dashboard Cite

This article systematically evaluates the influence of Artificial Intelligence (AI) on the landscape of Threat modelingin cybersecurity. The study involves an extensive review of relevant journal articles, books, and conference papers to comprehensively assess the current state of the field. By synthesizing existing literature, we identify and analyze the ways in which AItechnologies are applied in Threat modelingmethodologies. The evaluation explores the strengths and limitations of these applications, shedding light on the advancements that have significantly enhancedThreat modeling.Furthermore, the research includes a meticulous gap analysis within the existing literature, revealing areas where further investigation is warranted. Identified gaps in the current research landscape serve as a foundation for proposing future research directions in AI-enhanced Threat modeling. The current literature related to the current landscape of Artificial Intelligence research in cybersecurity predominantly focuses on articles and active studies pertaining to the detection and prevention of cyber-attacks. However, there is a noticeable gap in the existing literature when it comes to leveraging Artificial Intelligence to enhance Threat modeling. While numerous innovative methods have been proposed in recent articles, these predominantly concentrate on Threat modeling within specific domains, such as unmanned vehicles, Cyber-Physical Systems, and Healthcare. There is a lack of generalization in applying these findings to improve Threat modeling practices more broadly. A promising avenue for further research lies in the automation of Threat modeling. Existing literature predominantly emphasizes the study of Threat generation areas, leaving other crucial aspects, such as Architecture representation and Model validation,in need of more comprehensive exploration and analysis

show abstract

Data Privacy Threat Modelling for Autonomous Systems: A Survey From the GDPR's Perspective

Cited by 13 publications

References 195 publications

Hybrid Turbo-Shaft Engine Digital Twinning for Autonomous Aircraft via AI and Synthetic Data Generation

Hybrid Turbo-Shaft Engine Digital Twinning for Autonomous Aircraft via AI and Synthetic Data Generation

A Comprehensive Survey of Threats in Platooning—A Cloud-Assisted Connected and Autonomous Vehicle Application

A Systematic Evaluation of Artificial Intelligence's Impact on the Landscape of Threat Modeling

Contact Info

Product

Resources

About