Table of Links
Abstract and 1. Introduction
1.1 Background
1.2 Motivation
1.3 Our Work and Contributions and 1.4 Organization
-
Related Work
2.1 Mobile AIGC and Its QoE Modeling
2.2 Blockchain for Mobile Networks
-
Preliminaries
-
Prosecutor Design
4.1 Architecture Overview
4.2 Reputation Roll-up
4.3 Duplex Transfer Channel
-
OS2a: Objective Service Assessment for Mobile AIGC
5.1 Inspiration from DCM
5.2 Objective Quality of the Service Process
5.3 Subjective Experience of AIGC Outputs
-
OS2A on Prosecutor: Two-Phase Interaction for Mobile AIGC
6.1 MASP Selection by Reputation
6.2 Contract Theoretic Payment Scheme
-
Implementation and Evaluation
7.1 Implementation and Experimental Setup
7.2 Prosecutor Performance Evaluation
7.3 Investigation of Functional Goals
7.4 Security Analysis
-
Conclusion and References
7 IMPLEMENTATION AND EVALUATION
In this section, we elaborate on the implementation and evaluation. Firstly, we demonstrate the implementation of ProSecutor system. Then, we conduct extensive experiments to validate the architectural superiority of ProSecutor and prove that ProSecutor can effectively achieve all the design goals.
7.1 Implementation and Experimental Setup
Implementation. We implement the prototype of ProSecutor atop BlockEmulator[4], which is an open-source repository for building customized blockchain systems. Specifically, we extend BlockEmulator by implementing the reputation roll-up and duplex transfer channels illustrated in Section 4. Afterward, we deploy the OS2A framework, reputation-based MASP selection, and contract theoretic payment scheme on ProSecutor.
Testbed. To construct the mobile AIGC market, we build an eight-node ProSecutor cluster. The MASPs are served by Apple MacBook Pro with one 2.3 GHz 8-Core Intel Core i9 CPU and AMD Radeon Pro 5500M GPU. The mobile AIGC inferences are supported by Draw Things, an iOSoriented text-to-image AIGC application based on Stable Diffusion model. To fully simulate the real-world scenario we feed ProSecutor with one million historical Ethereum transactions in 2022. Finally, the baseline is the original version of BlockEmulator, which reproduces the traditional blockchain architecture, such as Bitcoin and Ethereum.
Questions. Through the experiments, we intend to answer the following research questions:
• Can reputation roll-up and duplex and transfer channels reduce the blockchain overhead, making ProSecutor adapt to the mobile environment (for G1)?
• Can ProSecutor, with the OS2A framework and mechanisms deployed on it, effectively realize all the functional goals, i.e., efficient MASP selection, payment scheme optimization, and atomic fee-ownership transfer (for G2, G3, G4)?
• Can ProSecutor defend the attacks and threats in the mobile AIGC, e.g., forking ledgers, forging reputation, and breaking transfers?
Authors:
(1) Yinqiu Liu, School of Computer Science and Engineering, Nanyang Technological University, Singapore ([email protected]);
(2) Hongyang Du, School of Computer Science and Engineering, Nanyang Technological University, Singapore ([email protected]);
(3) Dusit Niyato, School of Computer Science and Engineering, Nanyang Technological University, Singapore ([email protected]);
(4) Jiawen Kang, School of Automation, Guangdong University of Technology, China ([email protected]);
(5) Zehui Xiong, Pillar of Information Systems Technology and Design, Singapore University of Technology and Design, Singapore ([email protected]);
(6) Abbas Jamalipour, School of Electrical and Information Engineering, University of Sydney, Australia ([email protected]);
(7) Xuemin (Sherman) Shen, Department of Electrical and Computer Engineering, University of Waterloo, Canada ([email protected]).
[4] https://www.blockemulator.com/
