相关论文: BarraCUDA: Edge GPUs do Leak DNN Weights

In today's world, a vast amount of data is being generated by edge devices that can be used as valuable training data to improve the performance of machine learning algorithms in terms of the achieved accuracy or to reduce the compute…

One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks -- a trojan model responds to trigger-embedded inputs in a highly predictable manner while functioning normally otherwise. Despite…

Edge computing has emerged as an alternative to reduce transmission and processing delay and preserve privacy of the video streams. However, the ever-increasing complexity of Deep Neural Networks (DNNs) used in video-based applications…

A recently proposed class of materials, called software-defined metamaterials, can change their electromagnetic behavior on demand, utilizing a nanonetwork embedded in their structure. The present work focuses on 2D metamaterials, known as…

We propose distributed deep neural networks (DDNNs) over distributed computing hierarchies, consisting of the cloud, the edge (fog) and end devices. While being able to accommodate inference of a deep neural network (DNN) in the cloud, a…

The increased memory and processing capabilities of today's edge devices create opportunities for greater edge intelligence. In the domain of vision, the ability to adapt a Convolutional Neural Network's (CNN) structure and parameters to…

These notes accompany the open-source code published in GitHub which implements a GPU-based line-segment, surface-triangle intersection algorithm in CUDA. It mentions some relevant works and discusses issues specific to this implementation.…

Visual intelligence at the edge is becoming a growing necessity for low latency applications and situations where real-time decision is vital. Object detection, the first step in visual data analytics, has enjoyed significant improvements…

Bit-flip attacks (BFAs) can manipulate deep neural networks (DNNs). For high-level DNN models running on deep learning (DL) frameworks like PyTorch, extensive BFAs have been used to flip bits in model weights and shown effective. Defenses…

This paper presents a Gated Recurrent Unit (GRU) based recurrent neural network (RNN) accelerator called EdgeDRNN designed for portable edge computing. EdgeDRNN adopts the spiking neural network inspired delta network algorithm to exploit…

Deep Neural Networks (DNN) are gaining higher commercial values in computer vision applications, e.g., image classification, video analytics, etc. This calls for urgent demands of the intellectual property (IP) protection of DNN models. In…

In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that…

Dynamic graph neural network (DGNN) is becoming increasingly popular because of its widespread use in capturing dynamic features in the real world. A variety of dynamic graph neural networks designed from algorithmic perspectives have…

Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications. As…

Neural networks have become a fundamental component of numerous practical applications, and their implementations, which are often accelerated by hardware, are integrated into all types of real-world physical devices. User interactions with…

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes…

In neural network (NN) security, safeguarding model integrity and resilience against adversarial attacks has become paramount. This study investigates the application of stochastic computing (SC) as a novel mechanism to fortify NN models.…

Neural network training entails heavy computation with obvious bottlenecks. The Compute Unified Device Architecture (CUDA) programming model allows us to accelerate computation by passing the processing workload from the CPU to the graphics…

Face recognition is a rapidly developing and widely applied aspect of biometric technologies. Its applications are broad, ranging from law enforcement to consumer applications, and industry efficiency and monitoring solutions. The recent…

Computing at the edge is increasingly important since a massive amount of data is generated. This poses challenges in transporting all that data to the remote data centers and cloud, where they can be processed and analyzed. On the other…