Secure and trustworthy artificial intelligence-extended reality (AI-XR) for metaverses

A Qayyum, MA Butt, H Ali, M Usman, O Halabi… - ACM Computing …, 2024 - dl.acm.org
Metaverse is expected to emerge as a new paradigm for the next-generation Internet,
providing fully immersive and personalized experiences to socialize, work, and play in self …

[HTML][HTML] Resilience and resilient systems of artificial intelligence: taxonomy, models and methods

V Moskalenko, V Kharchenko, A Moskalenko… - Algorithms, 2023 - mdpi.com
Artificial intelligence systems are increasingly being used in industrial applications, security
and military contexts, disaster response complexes, policing and justice practices, finance …

Hardware and software optimizations for accelerating deep neural networks: Survey of current trends, challenges, and the road ahead

M Capra, B Bussolino, A Marchisio, G Masera… - IEEE …, 2020 - ieeexplore.ieee.org
Currently, Machine Learning (ML) is becoming ubiquitous in everyday life. Deep Learning
(DL) is already present in many applications ranging from computer vision for medicine to …

Qeba: Query-efficient boundary-based blackbox attack

H Li, X Xu, X Zhang, S Yang… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Abstract Machine learning (ML), especially deep neural networks (DNNs) have been widely
used in various applications, including several safety-critical ones (eg autonomous driving) …

Robust machine learning systems: Challenges, current trends, perspectives, and the road ahead

M Shafique, M Naseer, T Theocharides… - IEEE Design & …, 2020 - ieeexplore.ieee.org
Currently, machine learning (ML) techniques are at the heart of smart cyber-physical
systems (CPSs) and Internet-of-Things (loT). This article discusses various challenges and …

Stateful detection of black-box adversarial attacks

S Chen, N Carlini, D Wagner - Proceedings of the 1st ACM Workshop on …, 2020 - dl.acm.org
The problem of adversarial examples, evasion attacks on machine learning classifiers, has
proven extremely difficult to solve. This is true even in the black-box threat model, as is the …

Deep learning for edge computing: Current trends, cross-layer optimizations, and open research challenges

A Marchisio, MA Hanif, F Khalid… - 2019 IEEE Computer …, 2019 - ieeexplore.ieee.org
In the Machine Learning era, Deep Neural Networks (DNNs) have taken the spotlight, due to
their unmatchable performance in several applications, such as image processing, computer …

[HTML][HTML] Towards secure private and trustworthy human-centric embedded machine learning: An emotion-aware facial recognition case study

MA Butt, A Qayyum, H Ali, A Al-Fuqaha, J Qadir - Computers & Security, 2023 - Elsevier
The use of artificial intelligence (AI) at the edge is transforming every aspect of the lives of
human beings from scheduling daily activities to personalized shopping recommendations …

Towards query-efficient adversarial attacks against automatic speech recognition systems

Q Wang, B Zheng, Q Li, C Shen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Adversarial attacks, which attract explosive rese-arch attention in recent years, have
achieved fantastic success in fooling neural networks, especially for image-classification …

Towards energy-efficient and secure edge AI: A cross-layer framework ICCAD special session paper

M Shafique, A Marchisio, RVW Putra… - 2021 IEEE/ACM …, 2021 - ieeexplore.ieee.org
The security and privacy concerns along with the amount of data that is required to be
processed on regular basis has pushed processing to the edge of the computing systems …