Differential privacy for deep and federated learning: A survey

A El Ouadrhiri, A Abdelhadi - IEEE access, 2022 - ieeexplore.ieee.org
Users' privacy is vulnerable at all stages of the deep learning process. Sensitive information
of users may be disclosed during data collection, during training, or even after releasing the …

Backdoor attacks and countermeasures on deep learning: A comprehensive review

Y Gao, BG Doan, Z Zhang, S Ma, J Zhang, A Fu… - arXiv preprint arXiv …, 2020 - arxiv.org
This work provides the community with a timely comprehensive review of backdoor attacks
and countermeasures on deep learning. According to the attacker's capability and affected …

Cybersecurity of smart inverters in the smart grid: A survey

Y Li, J Yan - IEEE Transactions on Power Electronics, 2022 - ieeexplore.ieee.org
The penetration of distributed energy resources (DERs) in smart grids significantly increases
the number of field devices owned and controlled by consumers, aggregators, third parties …

A review of machine learning algorithms for cloud computing security

UA Butt, M Mehmood, SBH Shah, R Amin, MW Shaukat… - Electronics, 2020 - mdpi.com
Cloud computing (CC) is on-demand accessibility of network resources, especially data
storage and processing power, without special and direct management by the users. CC …

Intelligent disassembly of electric-vehicle batteries: a forward-looking overview

K Meng, G Xu, X Peng, K Youcef-Toumi, J Li - … , Conservation and Recycling, 2022 - Elsevier
Retired electric-vehicle lithium-ion battery (EV-LIB) packs pose severe environmental
hazards. Efficient recovery of these spent batteries is a significant way to achieve closed …

A systematic review on machine learning models for online learning and examination systems

S Kaddoura, DE Popescu, JD Hemanth - PeerJ Computer Science, 2022 - peerj.com
Examinations or assessments play a vital role in every student's life; they determine their
future and career paths. The COVID pandemic has left adverse impacts in all areas …

State-of-the-art and research opportunities for next-generation consumer electronics

CK Wu, CT Cheng, Y Uwate, G Chen… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
The tremendous advancement of Internet-of-Things (IoT) has proliferated the interaction
between the physical and cyber worlds. Consumer electronics, as the first tier in the physical …

Adversarial machine learning: A multilayer review of the state-of-the-art and challenges for wireless and mobile systems

J Liu, M Nogueira, J Fernandes… - … Surveys & Tutorials, 2021 - ieeexplore.ieee.org
Machine Learning (ML) models are susceptible to adversarial samples that appear as
normal samples but have some imperceptible noise added to them with the intention of …

NSL-MHA-CNN: a novel CNN architecture for robust diabetic retinopathy prediction against adversarial attacks

O Daanouni, B Cherradi, A Tmiri - IEEE Access, 2022 - ieeexplore.ieee.org
Convolution Neural Network (CNN) models have gained ground in research activities
particularly in medical images used for Diabetes Retinopathy (DR) detection. X-ray, MRI …

A survey of machine learning techniques in adversarial image forensics

E Nowroozi, A Dehghantanha, RM Parizi… - Computers & Security, 2021 - Elsevier
Image forensic plays a crucial role in both criminal investigations (eg, dissemination of fake
images to spread racial hate or false narratives about specific ethnicity groups or political …