OS2a: Objective Service Assessment for Mobile AIGC

Table of Links

Abstract and 1. Introduction

1.1 Background

1.2 Motivation

1.3 Our Work and Contributions and 1.4 Organization

2. Related Work

   2.1 Mobile AIGC and Its QoE Modeling

   2.2 Blockchain for Mobile Networks

3. Preliminaries

4. Prosecutor Design

   4.1 Architecture Overview

   4.2 Reputation Roll-up

   4.3 Duplex Transfer Channel

5. 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

6. OS2A on Prosecutor: Two-Phase Interaction for Mobile AIGC

   6.1 MASP Selection by Reputation

   6.2 Contract Theoretic Payment Scheme

7. Implementation and Evaluation

   7.1 Implementation and Experimental Setup

   7.2 Prosecutor Performance Evaluation

   7.3 Investigation of Functional Goals

   7.4 Security Analysis

8. Conclusion and References

5 OS2A: OBJECTIVE-SUBJECTIVE SERVICE ASSESSMENT FOR MOBILE AIGC

In this section, we elaborate on the design of the OS2A framework. Firstly, inspired by the DCM principle [15], we present the idea of OS2A. Then, we demonstrate the modeling of the objective service quality and subjective service experience, respectively.

5.1 Inspiration from DCM

The modeling of the quality and experience of AIGC services is intractable. For instance, Fig. 4 shows five AIGC images generated by the same prompt. Comparing Figs. 4(a) and (b), we can observe that the latter has higher “quality” since its cabin is located in the center and contains more details. However, from the client’s perspective, the experience of Fig. 4(b) might be poor since it may highly prefer photorealism images like Figs. 4(a) and (c)-(e) rather than cartoon-styled Fig. 4(b). Apart from preference, different clients may hold different standards for the AIGC services. Some are lenient, while others might be strict. Back to the above example, even for Figs. 4(d) and (e), the strict clients might claim that the cabin is too low and there draws the unexpected aurora, respectively. DCM, first presented by Daniel McFadden [15], explains the cause of such situations. This theory states that the power determining the clients’ utility comes from two collaborative sources, namely objective factors and subjective factors. The former indicates the objective attributes that clients can enjoy, while the latter is affected by the specific environment and the subjectivity of the clients themselves. Inspired by DCM, we present the concept of Objective-Subjective Service Assessment (OS2A) for mobile AIGC, considering both the objective experience of the AIGC service process and the subjective experience of the AIGC outputs. OS2A is defined as