With the rapid proliferation of Internet of Things systems, ensuring secure communication for those applications that need to exchange sensitive and/or critical data is one of the major issues to be faced. Traditional...
详细信息
ISBN:
(纸本)9798400704925
With the rapid proliferation of Internet of Things systems, ensuring secure communication for those applications that need to exchange sensitive and/or critical data is one of the major issues to be faced. Traditional security mechanisms are often impractical due to the constrained resources typically available on IoT devices. On the other hand, Physical Unclonable Functions are emerging as one of the most promising technologies to address security-related challenges. In this manuscript, we propose a novel scheme leveraging PUF-chains to facilitate key agreement between two devices. The scheme employs a trusted third party for secure communications;additionally, it facilitates seamless and continuous modification of the cryptographic key employed, by resulting really suitable in systems for moving target defense. To demonstrate the feasibility of our proposal, we take into account an implementation of the solution on resource-constrained devices, specifically ESP8266, and conducted a thorough analysis in terms of communication and computational costs, time orhead and formal security verification.
In the era of rapidly expanding image data, the demand for improved image compression algorithms has grown significantly, particularly with the integration of deep learning approaches into traditional image processing...
详细信息
ISBN:
(纸本)9781510673854;9781510673847
In the era of rapidly expanding image data, the demand for improved image compression algorithms has grown significantly, particularly with the integration of deep learning approaches into traditional image processing tasks. However, many of the existing solutions in this domain are burdened by computational complexity, rendering them unsuitable for real-time deployment on standard devices as they often necessitate complex systems and substantial energy consumption. This work addresses the growing paradigm of edge computing for real-time applications by introducing a novel, on-edge device solution. This innovative approach aims to strike a balance between efficiency and accuracy, adhering to the practical constraints of real-world deployment. By presenting demonstrations of the proposed solution's performance on readily available devices, we provide tangible evidence of its applicability and viability in real-world scenarios. This advance contributes to the ongoing dialogue about the need for accessible and efficient image compression algorithms that can be deployed real-time applications on edge devices, bridging the gap between the demanding computational requirements of deep learning and the practical limitations of everyday hardware. As data continues to surge, solutions like this become ever more critical in ensuring effective image compression, aligning with on-edge computing within AI. This research paves the way for improved image processing in real-time applications while conserving computational resources and energy consumption.
Quantum Reinforcement Learning (QRL) is an emerging field with many novel approaches suitable for noisy intermediate-scale quantum (NISQ) devices being proposed recently. Projective Simulation (PS) is a classical mach...
详细信息
ISBN:
(纸本)9798331541378
Quantum Reinforcement Learning (QRL) is an emerging field with many novel approaches suitable for noisy intermediate-scale quantum (NISQ) devices being proposed recently. Projective Simulation (PS) is a classical machine learning method based on random walks in a Directed Acyclic Graph (DAG), and is mainly used to train agents in a Reinforcement Learning setup. This graph corresponds to the Episodic Compositional Memory (ECM) of the agent. For the quantum version of PS we use quantum walks of single photons in quantum optical circuits, which go through tunable components (beamsplitters and phase shifters). We call this specific model Quantum Optical Projective Simulation (QOPS). In this work, we propose a general framework to translate any 2-layer ECM to a quantum optical circuit and an algorithm for solving quantum strategic games using QOPS. Moreover, we introduce QOPS with an entangled state as input. The application that we are using to evaluate the performance of the framework is the Prisoner's Dilemma. We executed the implementation using Altair's noisy simulator, designed to emulate a single photon-based quantum processor by Quandela. The algorithm provided promising results even in the presence of noise, which makes it a strong candidate for runs on single-photon -based quantum processors.
The emergence of the COVID-19 epidemic has emphasized the continuous need for innovative and discreet methods to monitor and evaluate the progression of the disease. Wearable technology, equipped with an array of sens...
详细信息
Deep neural networks are an established class of algorithms widely used for real-time data analysis in computer vision-based mobile applications. However, on one hand the constrained resources - computing power, energ...
详细信息
ISBN:
(纸本)9798350374247;9798350374230
Deep neural networks are an established class of algorithms widely used for real-time data analysis in computer vision-based mobile applications. However, on one hand the constrained resources - computing power, energy reservoir and memory - available to mobile devices clash with the complexity of high-performance neural models. On the other hand, offloading the execution of the computing task to a wirelessly connected edge/cloud server requires the transfer of information rich signals over volatile and capacity constrained channels. To address this issue, the Split computing (SC) paradigm has been proposed. In SC frameworks, a baseline DNN model is used to create two models, namely head and tail models, that are executed at a mobile device and edge/cloud server, respectively. In this work, a SC paradigm - Condar - is presented that introduces several core design and conceptual innovations: (i) we target object detection on radar data rather than 2D RGB images;(ii) we design encoders/decoder structures that are specialized to the specific operating environment;(iii) we develop a multi-branched model that can dynamically select the best performing encoder while executing the main model. Our design is based on the CenterNet model with a split ResNet50 backbone trained on the RADIATE dataset's radar images of resolution 1152x1152. Our results show that Condar has performance analogous to that of a Generalized CenterNet Model with a difference of 4.41%, 1.72%, and 2.18% on mAP@50, mAP@75, and mAP@COCO respectively, while simultaneously performing compression on the features of the data to 15.5KB. This datasize is smaller than lowest possible compression data size of JPEG compression at 21KB, which results in a considerable performance degradation.
Artificial Intelligence (AI) is becoming increasingly important and pervasive in the modern world. The widespread adoption of AI algorithms is reflected in the extensive range of HW devices on which they can be deploy...
详细信息
The convergence of edge computing and artificial intelligence requires that inference is performed on-device to provide rapid response with low latency and high accuracy without transferring large amounts of data to t...
详细信息
ISBN:
(纸本)9798350364613;9798350364606
The convergence of edge computing and artificial intelligence requires that inference is performed on-device to provide rapid response with low latency and high accuracy without transferring large amounts of data to the cloud. However, power and size limitations make it challenging for electrical accelerators to support both inference and training for large neural network models. To this end, we propose Trident, a low-power photonic accelerator that combines the benefits of phase change material (PCM) and photonics to implement both inference and training in one unified architecture. Emerging silicon photonics has the potential to exploit the parallelism of neural network models, reduce power consumption and provide high bandwidth density via wavelength division multiplexing, making photonics an ideal candidate for on-device training and inference. As PCM is recoilfigurable and non-volatile, we utilize it for two distinct purposes: (i) to maintain resonant wavelength without expensive electrical or thermal heaters, and (ii) to implement non-linear activation function, which eliminates the need to move data between memory and compute units. This multi-purpose use of PCM is shown to lead to significant reduction in energy consumption and execution time. Compared to photonic accelerators DEAP-CNN, CrossLight, and PIXEL, Trident improves energy efficiency by up to 43% and latency by up to 150% on average. Compared to electronic edge AI accelerators Google Coral which utilizes the Google Edge TPU and Bearkey TB96-AL Trident improves energy efficiency by 11% and 93% respectively. While NVIDIA AGX Xavier is more energy efficient, the reduced data movement and GST activation of Trident reduce latency by 107% on average compared to the NVIDIA accelerator. When compared to the Google Coral and the Bearkey TB96-AI, Trident reduces latency by 1413% and 595% on average.
Mobile edge computing (MEC) allows terminals to send tasks to adjacent edge servers for calculation to reduce the burden on terminals and task completion time. With the widespread use of wireless devices (WDs) and the...
详细信息
ISBN:
(数字)9789819708017
ISBN:
(纸本)9789819708000;9789819708017
Mobile edge computing (MEC) allows terminals to send tasks to adjacent edge servers for calculation to reduce the burden on terminals and task completion time. With the widespread use of wireless devices (WDs) and the increasing complexity of applications, how to partially offload tasks to minimize task completion time has become a huge challenge. We propose a sequenced quantization based on recurrent neural network (SQ-RNN) algorithm that makes reasonable partial offload decisions for subtasks with dependencies. Specifically, the SQ-RNN algorithm first inputs the environment information into the RNN, and uses the RNN to generate a task offloading strategy. Then the algorithm quantifies the offloading strategy generated by the RNN into multiple binary offloading actions according to a certain method, and selects the action with the lowest computational delay from the multiple binary offloading actions as the offloading decision of the task. In addition, the algorithm also configs RNN with a fixed-size memory space to store the latest unloading strategy generated by RNN for further training of RNN. Experiments have proved that the SQ-RNN offloading algorithm described in our study generates better offloading decisions than those made by conventional offloading techniques.
Multi-access edge computing(MEC) enables computation task offloading and data processing at close proximity to provide rich endusers services with ultra-low latency in Internet of things(IoT). However, the high hetero...
详细信息
ISBN:
(数字)9789819708017
ISBN:
(纸本)9789819708000;9789819708017
Multi-access edge computing(MEC) enables computation task offloading and data processing at close proximity to provide rich endusers services with ultra-low latency in Internet of things(IoT). However, the high heterogeneity of the edge node configuration and the diversity of services pose challenges in fully utilizing the computing capacity in MEC. In this paper, we consider the problem of service-aware cooperative task offloading and scheduling in a three-tier MEC empowered IoT where the service requests from IoT devices can be distributed among edge nodes or further offloaded to remote cloud. As this problem is proven to be NP-hard, we proposed a two-layer Cooperative workload Initialization and Distribution Algorithm (CIDA) to solve the problem with low time complexity by decomposing it into two subproblems: 1) the optimization problem of offloading profile under dynamic resource allocation determined by the workload type, and 2) optimization problem of computation resources allocation under given offloading profile. Extensive experiments demonstrate that CIDA achieves superior performance compared to other approaches and scales well as the system size increases.
As cloud computing continues to evolve, computational power leasing has emerged as a novel web service model, providing users with access to computing resources or cloud computing capabilities. This enables users to o...
详细信息
ISBN:
(纸本)9789819756650;9789819756667
As cloud computing continues to evolve, computational power leasing has emerged as a novel web service model, providing users with access to computing resources or cloud computing capabilities. This enables users to offload their computational tasks to remote devices and retrieve results. However, with the exponential growth in data generation, cloud service providers are confronted with the critical challenge of differentiating malicious code within a vast array of computing tasks. To address this issue, this paper proposes a comprehensive lifecycle malicious code detection framework that integrates Runtime Application Self-Protection (RASP) with random forest technology, facilitating rapid and accurate identification of malicious code. Experimental results demonstrate that the intelligent detection process using random forest yields better performance compared to other machine learning algorithms. By training the intelligent detection model with features selected in this paper, a high accuracy rate of up to 95.10% is achieved on the collected G4 sample set. Additionally, the proposed framework achieves the highest accuracy rate among other schemes on the G1 sample set, reaching 98.07%. This research offers an effective security measure for computational power leasing providers in this domain.
暂无评论