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 …
normal samples but have some imperceptible noise added to them with the intention of …
Evolutionary deep learning: A survey
As an advanced artificial intelligence technique for solving learning problems, deep learning
(DL) has achieved great success in many real-world applications and attracted increasing …
(DL) has achieved great success in many real-world applications and attracted increasing …
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 …
particularly in medical images used for Diabetes Retinopathy (DR) detection. X-ray, MRI …
Bayesian evolutionary optimization for crafting high-quality adversarial examples with limited query budget
Due to the importance of security, the adversarial attack has become an increasingly
popular area for deep learning, especially the black-box adversarial attack, which can only …
popular area for deep learning, especially the black-box adversarial attack, which can only …
A robust deep-learning-enabled trust-boundary protection for adversarial industrial IoT environment
In recent years, trust-boundary protection has become a challenging problem in Industrial
Internet of Things (IIoT) environments. Trust boundaries separate IIoT processes and data …
Internet of Things (IIoT) environments. Trust boundaries separate IIoT processes and data …
Lightweight actor-critic generative adversarial networks for real-time smart generation control of microgrids
K Han, K Yang, L Yin - Applied Energy, 2022 - Elsevier
Large-scale introduction of new energy could effectively alleviate energy shortage and
environmental pollution. However, the uncertainty of wind and solar energy brings serious …
environmental pollution. However, the uncertainty of wind and solar energy brings serious …
Remix: Towards the transferability of adversarial examples
Deep neural networks (DNNs) are susceptible to adversarial examples, which are crafted by
deliberately adding some human-imperceptible perturbations on original images. To explore …
deliberately adding some human-imperceptible perturbations on original images. To explore …
Boosting the transferability of adversarial examples via stochastic serial attack
Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by
imposing mild perturbation on clean ones. An intriguing property of adversarial examples is …
imposing mild perturbation on clean ones. An intriguing property of adversarial examples is …
Adversarial attacks in computer vision: a survey
Deep learning, as an important topic of artificial intelligence, has been widely applied in
various fields, especially in computer vision applications, such as image classification and …
various fields, especially in computer vision applications, such as image classification and …
DEFEAT: Decoupled feature attack across deep neural networks
L Huang, C Gao, N Liu - Neural Networks, 2022 - Elsevier
Adversarial attacks pose a security challenge for deep neural networks, motivating
researchers to build various defense methods. Consequently, the performance of black-box …
researchers to build various defense methods. Consequently, the performance of black-box …