Developing future human-centered smart cities: Critical analysis of smart city security, Data management, and Ethical challenges

K Ahmad, M Maabreh, M Ghaly, K Khan, J Qadir… - Computer Science …, 2022 - Elsevier
As the globally increasing population drives rapid urbanization in various parts of the world,
there is a great need to deliberate on the future of the cities worth living. In particular, as …

A multidisciplinary survey and framework for design and evaluation of explainable AI systems

S Mohseni, N Zarei, ED Ragan - ACM Transactions on Interactive …, 2021 - dl.acm.org
The need for interpretable and accountable intelligent systems grows along with the
prevalence of artificial intelligence (AI) applications used in everyday life. Explainable AI …

Uncertainties in onboard algorithms for autonomous vehicles: Challenges, mitigation, and perspectives

K Yang, X Tang, J Li, H Wang, G Zhong… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Autonomous driving is considered one of the revolutionary technologies shaping humanity's
future mobility and quality of life. However, safety remains a critical hurdle in the way of …

Software verification and validation of safe autonomous cars: A systematic literature review

N Rajabli, F Flammini, R Nardone, V Vittorini - IEEE Access, 2020 - ieeexplore.ieee.org
Autonomous, or self-driving, cars are emerging as the solution to several problems primarily
caused by humans on roads, such as accidents and traffic congestion. However, those …

Sources of risk of AI systems

A Steimers, M Schneider - … Journal of Environmental Research and Public …, 2022 - mdpi.com
Artificial intelligence can be used to realise new types of protective devices and assistance
systems, so their importance for occupational safety and health is continuously increasing …

Formal methods and validation techniques for ensuring automotive systems security

M Krichen - Information, 2023 - mdpi.com
The increasing complexity and connectivity of automotive systems have raised concerns
about their vulnerability to security breaches. As a result, the integration of formal methods …

Taxonomy of machine learning safety: A survey and primer

S Mohseni, H Wang, C Xiao, Z Yu, Z Wang… - ACM Computing …, 2022 - dl.acm.org
The open-world deployment of Machine Learning (ML) algorithms in safety-critical
applications such as autonomous vehicles needs to address a variety of ML vulnerabilities …

[HTML][HTML] Cyber attack detection for self-driving vehicle networks using deep autoencoder algorithms

FW Alsaade, MH Al-Adhaileh - Sensors, 2023 - mdpi.com
Connected and autonomous vehicles (CAVs) present exciting opportunities for the
improvement of both the mobility of people and the efficiency of transportation systems. The …

A comparison of uncertainty estimation approaches in deep learning components for autonomous vehicle applications

F Arnez, H Espinoza, A Radermacher… - arXiv preprint arXiv …, 2020 - arxiv.org
A key factor for ensuring safety in Autonomous Vehicles (AVs) is to avoid any abnormal
behaviors under undesirable and unpredicted circumstances. As AVs increasingly rely on …

A unified benchmark for the unknown detection capability of deep neural networks

J Kim, J Koo, S Hwang - Expert Systems with Applications, 2023 - Elsevier
Deep neural networks have achieved outstanding performance over various tasks, but they
have a critical issue: over-confident predictions even for completely unknown samples …