Hardware and software optimizations for accelerating deep neural networks: Survey of current trends, challenges, and the road ahead
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 …
(DL) is already present in many applications ranging from computer vision for medicine to …
Qeba: Query-efficient boundary-based blackbox attack
Abstract Machine learning (ML), especially deep neural networks (DNNs) have been widely
used in various applications, including several safety-critical ones (eg autonomous driving) …
used in various applications, including several safety-critical ones (eg autonomous driving) …
Robust machine learning systems: Challenges, current trends, perspectives, and the road ahead
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 …
systems (CPSs) and Internet-of-Things (loT). This article discusses various challenges and …
Stateful detection of black-box adversarial attacks
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 …
proven extremely difficult to solve. This is true even in the black-box threat model, as is the …
Building robust machine learning systems: Current progress, research challenges, and opportunities
Machine learning, in particular deep learning, is being used in almost all the aspects of life
to facilitate humans, specifically in mobile and Internet of Things (IoT)-based applications …
to facilitate humans, specifically in mobile and Internet of Things (IoT)-based applications …
Deep learning for edge computing: Current trends, cross-layer optimizations, and open research challenges
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 …
their unmatchable performance in several applications, such as image processing, computer …
Towards query-efficient adversarial attacks against automatic speech recognition systems
Adversarial attacks, which attract explosive rese-arch attention in recent years, have
achieved fantastic success in fooling neural networks, especially for image-classification …
achieved fantastic success in fooling neural networks, especially for image-classification …
Qusecnets: Quantization-based defense mechanism for securing deep neural network against adversarial attacks
Adversarial examples have emerged as a significant threat to machine learning algorithms,
especially to the convolutional neural networks (CNNs). In this paper, we propose two …
especially to the convolutional neural networks (CNNs). In this paper, we propose two …
Fadec: A fast decision-based attack for adversarial machine learning
Due to the excessive use of cloud-based machine learning (ML) services, the smart cyber-
physical systems (CPS) are increasingly becoming vulnerable to black-box attacks on their …
physical systems (CPS) are increasingly becoming vulnerable to black-box attacks on their …
TrISec: training data-unaware imperceptible security attacks on deep neural networks
Most of the data manipulation attacks on deep neural networks (DNNs) during the training
stage introduce a perceptible noise that can be catered by preprocessing during inference …
stage introduce a perceptible noise that can be catered by preprocessing during inference …