Adversarial machine learning (AML) attacks have become a major concern for organizations
in recent years, as AI has become the industry's focal point and GenAI applications have …

Quantization is promising in enabling powerful yet complex deep neural networks (DNNs) to
be deployed into resource constrained platforms. However, quantized DNNs are vulnerable …

The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of
Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices …

Neural networks are getting deeper and more computation-intensive nowadays.
Quantization is a useful technique in deploying neural networks on hardware platforms and …

Neural networks are getting better accuracy with higher energy and computational cost. After
quantization, the cost can be greatly saved, and the quantized models are more hardware …

Recent studies have revealed that Machine Learning (ML) models are vulnerable to
adversarial perturbations. Such perturbations can be intentionally or accidentally added to …

Enhancing dehaze method in real hill based images using Gaussian filter over gabor filter
for better exactness. The Gaussian filter (N= 10) and gabor filter method (N= 10) these two …

The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of
Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices …

ML models are widely used in real-world applications, but their increasing complexity has
made them opaque black boxes, hindering their safe adoption in critical areas. This thesis …

Deep learning and neural networks have great potential while still at risk. The so-called
adversarial attacks, which apply small perturbations on input samples to fool models …