Evasion Attack and Defense On Machine Learning Models in Cyber-Physical Systems: A Survey
Cyber-physical systems (CPS) are increasingly relying on machine learning (ML)
techniques to reduce labor costs and improve efficiency. However, the adoption of ML also …
techniques to reduce labor costs and improve efficiency. However, the adoption of ML also …
[HTML][HTML] Impact of autoencoder based compact representation on emotion detection from audio
Emotion recognition from speech has its fair share of applications and consequently
extensive research has been done over the past few years in this interesting field. However …
extensive research has been done over the past few years in this interesting field. However …
Adversarial attack and training for deep neural network based power quality disturbance classification
L Zhang, C Jiang, Z Chai, Y He - Engineering Applications of Artificial …, 2024 - Elsevier
Power quality disturbance (PQD) can significantly affect the normal operation of the power
system. Deep neural network (DNN) can classify PQD with extremely high accuracy …
system. Deep neural network (DNN) can classify PQD with extremely high accuracy …
Topological safeguard for evasion attack interpreting the neural networks' behavior
X Echeberria-Barrio, A Gil-Lerchundi, I Mendialdua… - Pattern Recognition, 2024 - Elsevier
In the last years, Deep Learning technology has been proposed in different fields, bringing
many advances in each of them, but raising new threats in these solutions regarding …
many advances in each of them, but raising new threats in these solutions regarding …
Projected randomized smoothing for certified adversarial robustness
Randomized smoothing is the current state-of-the-art method for producing provably robust
classifiers. While randomized smoothing typically yields robust $\ell_2 $-ball certificates …
classifiers. While randomized smoothing typically yields robust $\ell_2 $-ball certificates …
Defending adversarial attacks on deep learning-based power allocation in massive MIMO using denoising autoencoders
Recent work has advocated for the use of deep learning to perform power allocation in the
downlink of massive MIMO (maMIMO) networks. Yet, such deep learning models are …
downlink of massive MIMO (maMIMO) networks. Yet, such deep learning models are …
A deep learning model for burn depth classification using ultrasound imaging
S Lee, J Lukan, T Boyko, K Zelenova, B Makled… - Journal of the …, 2022 - Elsevier
Identification of burn depth with sufficient accuracy is a challenging problem. This paper
presents a deep convolutional neural network to classify burn depth based on altered tissue …
presents a deep convolutional neural network to classify burn depth based on altered tissue …
Denoising and verification cross-layer ensemble against black-box adversarial attacks
Deep neural networks (DNNs) have demonstrated impressive performance on many
challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs …
challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs …
Evaluating the adversarial robustness of text classifiers in hyperdimensional computing
Hyperdimensional (HD) Computing leverages random high dimensional vectors (> 10000
dimensions) known as hypervectors for data representation. This high dimensional feature …
dimensions) known as hypervectors for data representation. This high dimensional feature …
Super-efficient detector and defense method for adversarial attacks in power quality classification
L Zhang, C Jiang, A Pang, Y He - Applied Energy, 2024 - Elsevier
The correct classification of power quality (PQ) is the key step to ensure the normal
operation of smart grid. Deep neural networks have been widely used for PQ classification …
operation of smart grid. Deep neural networks have been widely used for PQ classification …