A New Standard for Mobile AIGC Security

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

8 CONCLUSION

In this paper, we presented ProSecutor, the first blockchain system for protecting mobile AIGC. Specifically, contributed to roll-up and layer-2 channels, ProSecutor achieves high performance and resource efficiency to adapt to the mobile environment. With ProSecutor, we first proposed the atomic fee-ownership transfer protocol, defending the repudiation in trustless mobile networks. Then, we presented a novel framework for QoE modeling in mobile AIGC, called OS2A. By fusing objective service KPIs and reputation-based subjective experience, OS2A can efficiently evaluate the AIGC services and guide clients to select the MASP with the highest probability of providing satisfying AIGC outputs. Moreover, we utilized contract theory to help clients optimize payment scheme design and circumvent the moral hazard. Extensive experiments demonstrated the effectiveness and validity of ProSecutor.

Future Work: For the future work, ProSecutor can be improved from the following aspects. First, the underlying architecture of ProSecutor can be updated to sharding blockchain, further improving the throughput and resource efficiency. Secondly, more objective KPIs oriented to Mobile AIGC can be integrated into OS2A, thus increasing the effectiveness of AIGC service assessment. Finally, the human feedback can be incorporated into the diffusion-DRL, thus making the decisions align with user preferences.

REFERENCES

[1] Y. Liu, H. Du, D. Niyato, J. Kang, Z. Xiong, C. Miao, Xuemin, Shen, and A. Jamalipour, “Blockchain-empowered lifecycle management for ai-generated content (aigc) products in edge networks,” IEEE Wireless Communications, accepted, 2023.

[2] Acumen projection for the global aigc market size. 2023. [Online]. Available: https://www.acumenresearchandconsulting. com/generative-ai-market

[3] S. Verma, T. K. Rodrigues, Y. Kawamoto, and N. Kato, “A survey on multi-ap coordination approaches over emerging wlans: Future directions and open challenges,” 2023. [Online]. Available: https://arxiv.org/abs/2306.04164

[4] Google on-device stable diffusion. 2023. [Online]. Available: https://developers.google.com/mediapipe

[5] Y.-H. Chen, R. Sarokin, J. Lee, J. Tang, C.-L. Chang, A. Kulik, and M. Grundmann, “Speed is all you need: On-device acceleration of large diffusion models via gpu-aware optimizations,” in IEEE/CVF CVPR, 2023, pp. 4650–4654.

[6] M. Xu, H. Du, D. Niyato, J. Kang, Z. Xiong, S. Mao, Z. Han, A. Jamalipour, D. I. Kim, Xuemin, Shen, V. C. M. Leung, and H. V. Poor, “Unleashing the power of edge-cloud generative ai in mobile networks: A survey of aigc services,” IEEE Communications Surveys and Tutorials, accepted, 2024.

[7] H. Du, Z. Li, D. Niyato, J. Kang, Z. Xiong, and H. Huang, “Generative ai-aided optimization for ai-generated content (aigc) services in edge networks,” IEEE Transactions on Mobile Computing, accepted, 2024.

[8] A. A. Barakabitze, N. Barman, A. Ahmad, S. Zadtootaghaj, L. Sun, M. G. Martini, and L. Atzori, “Qoe management of multimedia streaming services in future networks: A tutorial and survey,” IEEE Communications Surveys & Tutorials, vol. 22, no. 1, pp. 526– 565, 2020.

[9] M. A. Usman, S. Y. Shin, M. Shahid, and B. Lovstrom, “A no reference video quality metric based on jerkiness estimation focusing on multiple frame freezing in video streaming,” IETE Technical Review, vol. 34, no. 3, pp. 309–320, 2017.

[10] G. Bingol, S. Porcu, A. Floris, and L. Atzori, “Qoe estimation of ¨ webrtc-based audiovisual conversations from facial expressions,” in SITIS, 2022, pp. 577–584.

[11] S. Porcu, A. Floris, J.-N. Voigt-Antons, L. Atzori, and S. Moller, “Estimation of the quality of experience during video streaming from facial expression and gaze direction,” IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2702–2716, 2020.

[12] Pytorch library for image quality assessment. 2023. [Online]. Available: https://pypi.org/project/piq/0.5.1/

[13] Y. Tao, J. Qiu, and S. Lai, “Deep reinforcement learning based bidding strategy for evas in local energy market considering information asymmetry,” IEEE Transactions on Industrial Informatics, vol. 18, no. 6, pp. 3831–3842, 2022.

[14] Y. Wasa, K. Hirata, and K. Uchida, “A contract theory approach to dynamic incentive mechanism and control synthesis for moral hazard in power grids,” IEEE Transactions on Control Systems Technology, vol. 30, no. 5, pp. 2072–2083, 2022.

[15] The discrete choice modeling. 2023. [Online]. Available: https: //en.wikipedia.org/wiki/Choice modelling

[16] J. Kang, Z. Xiong, D. Niyato, S. Xie, and J. Zhang, “Incentive mechanism for reliable federated learning: A joint optimization approach to combining reputation and contract theory,” IEEE Internet of Things Journal, vol. 6, no. 6, pp. 10 700–10 714, 2019.

[17] L. T. Thibault, T. Sarry, and A. S. Hafid, “Blockchain scaling using rollups: A comprehensive survey,” IEEE Access, vol. 10, pp. 93 039– 93 054, 2022.

[18] J. Zhang, Y. Ye, W. Wu, and X. Luo, “Boros: Secure and efficient off-blockchain transactions via payment channel hub,” IEEE Transactions on Dependable and Secure Computing, vol. 20, no. 1, pp. 407– 421, 2023.

[19] The world’s first on-device diffusion. 2023. [Online]. Available: https://www.qualcomm.com/news/onq/2023/02/worlds-first-on-device-demonstration-of-stable-diffusion-on-android

[20] Y. Li, H. Wang, Q. Jin, J. Hu, P. Chemerys, Y. Fu, Y. Wang, S. Tulyakov, and J. Ren, “Snapfusion: Text-to-image diffusion model on mobile devices within two seconds,” 2023. [Online]. Available: https://arxiv.org/abs/2306.00980

[21] M. M. Bradley and P. J. Lang, “Measuring emotion: The self-assessment manikin and the semantic differential,” Journal of Behavior Therapy and Experimental Psychiatry, vol. 25, no. 1, pp. 49–59, 1994.

[22] M. S. Sara Vlahovic and L. Skorin-Kapov, “A survey of challenges and methods for quality of experience assessment of interactive vr applications,” Journal on Multimodal User Interfaces, vol. 16, pp. 257–291, 2022.

[23] The introduction to weber-fechner law. 2023. [Online]. Available: https://en.wikipedia.org/wiki/Weber–Fechner law

[24] H. Talebi and P. Milanfar, “Nima: Neural image assessment,” IEEE Transactions on Image Processing, vol. 27, no. 8, pp. 3998–4011, 2018.

[25] J. Li, J. Wu, L. Chen, J. Li, and S.-K. Lam, “Blockchain-based secure key management for mobile edge computing,” IEEE Transactions on Mobile Computing, vol. 22, no. 1, pp. 100–114, 2023.

[26] C. T. Nguyen, D. N. Nguyen, D. T. Hoang, H.-A. Pham, N. H. Tuong, Y. Xiao, and E. Dutkiewicz, “Blockroam: Blockchain-based roaming management system for future mobile networks,” IEEE Transactions on Mobile Computing, vol. 21, no. 11, pp. 3880–3894, 2022.

[27] S. Yao, M. Wang, Q. Qu, Z. Zhang, Y.-F. Zhang, K. Xu, and M. Xu, “Blockchain-empowered collaborative task offloading for cloud-edge-device computing,” IEEE Journal on Selected Areas in Communications, vol. 40, no. 12, pp. 3485–3500, 2022.

[28] B. An, M. Xiao, A. Liu, Y. Xu, X. Zhang, and Q. Li, “Secure crowdsensed data trading based on blockchain,” IEEE Transactions on Mobile Computing, vol. 22, no. 3, pp. 1763–1778, 2023.

[29] L. Xue, W. Yang, W. Chen, and L. Huang, “Stbc: A novel blockchain-based spectrum trading solution,” IEEE Transactions on Cognitive Communications and Networking, vol. 8, no. 1, pp. 13–30, 2022.

[30] Y. Liu, K. Wang, Y. Lin, and W. Xu, “LightChain: A lightweight blockchain system for industrial internet of things,” IEEE Transactions on Industrial Informatics, vol. 15, no. 6, pp. 3571–3581, 2019.

[31] S. Verma, Y. Kawamoto, and N. Kato, “A smart internet-wide port scan approach for improving iot security under dynamic wlan environments,” IEEE Internet of Things Journal, vol. 9, no. 14, pp. 11 951–11 961, 2022.

[32] M. U. Zaman, T. Shen, and M. Min, “Proof of sincerity: A new lightweight consensus approach for mobile blockchains,” in IEEE CCNC, 2019, pp. 1–4.

[33] C. Xu, K. Wang, P. Li, S. Guo, J. Luo, B. Ye, and M. Guo, “Making big data open in edges: A resource-efficient blockchain-based approach,” IEEE Transactions on Parallel and Distributed Systems, vol. 30, no. 4, pp. 870–882, 2019.

[34] A. Asheralieva and D. Niyato, “Reputation-based coalition formation for secure self-organized and scalable sharding in iot blockchains with mobile-edge computing,” IEEE Internet of Things Journal, vol. 7, no. 12, pp. 11 830–11 850, 2020.

[35] Q. Wang, C. Zhang, L. Wei, and Y. Xie, “Hyperchannel: A secure layer-2 payment network for large-scale iot ecosystem,” in IEEE ICC, 2021, pp. 1–6.

[36] A. Asheralieva and D. Niyato, “Learning-based mobile edge computing resource management to support public blockchain networks,” IEEE Transactions on Mobile Computing, vol. 20, no. 3, pp. 1092–1109, 2021.

[37] S. Jiang, X. Li, and J. Wu, “Multi-leader multi-follower stackelberg game in mobile blockchain mining,” IEEE Transactions on Mobile Computing, vol. 21, no. 6, pp. 2058–2071, 2022.

[38] S. Verma, Y. Kawamoto, and N. Kato, “Energy-efficient group paging mechanism for qos constrained mobile iot devices over ltea pro networks under 5g,” IEEE Internet of Things Journal, vol. 6, no. 5, pp. 9187–9199, 2019.

[39] M. Zamani, M. Movahedi, and M. Raykova, “Rapidchain: Scaling blockchain via full sharding,” in ACM CCS, 2018, p. 931–948.

[40] E. Kokoris-Kogias, P. Jovanovic, L. Gasser, N. Gailly, E. Syta, and B. Ford, “Omniledger: A secure, scale-out, decentralized ledger via sharding,” in IEEE SP, 2018, pp. 583–598.

[41] S. Verma, Y. Kawamoto, and N. Kato, “A network-aware internetwide scan for security maximization of ipv6-enabled wlan iot devices,” IEEE Internet of Things Journal, vol. 8, no. 10, pp. 8411– 8422, 2021.

[42] Y. Liu, K. Qian, K. Wang, and L. He, “Effective scaling of blockchain beyond consensus innovations and moore’s law: Challenges and opportunities,” IEEE Systems Journal, vol. 16, no. 1, pp. 1424–1435, 2022.

[43] Introduction ipfs. 2023. [Online]. Available: https://docs.ipfs.tech/concepts/what-is-ipfs/

[44] S. Li, Y. Zhang, C. Xu, N. Cheng, Z. Liu, Y. Du, and X. Shen, “Healthfort: A cloud-based ehealth system with conditional forward transparency and secure provenance via blockchain,” IEEE Transactions on Mobile Computing, pp. 1–18, 2022.

[45] I. Eyal, A. E. Gencer, E. G. Sirer, and R. V. Renesse, “Bitcoin-NG: A scalable blockchain protocol,” in 13th USENIX NSDI, 2016, pp. 45–59.

[46] The copyright of aigc products. 2023. [Online]. Available: https://docs.midjourney.com/docs/terms-of-service

[47] F. Wilhelmi, S. Barrachina-Munoz, and P. Dini, “End-to-end latency analysis and optimal block size of proof-of-work blockchain 17 applications,” IEEE Communications Letters, vol. 26, no. 10, pp. 2332–2335, 2022.

[48] A. Donmez and A. Karaivanov, “Transaction fee economics in the ethereum blockchain,” Economic Inquiry, vol. 60, no. 1, pp. 265–292, 2022.

[49] J. Guo, Z. Jiang, L. Li, and J. Bian, “Mathematical modeling of transaction latency on ethereum,” in IEEE JCC, 2021, pp. 34–37.

[50] The introduction to little’s law. 2023. [Online]. Available: https://en.wikipedia.org/wiki/Little's law

[51] The introduction to gamma function. 2023. [Online]. Available: https://www.britannica.com/science/gamma-function

[52] Introduction to heaviside step function. 2023. [Online]. Available: https://en.wikipedia.org/wiki/Heaviside step function

[53] Y. Wang, J. Yang, T. Li, F. Zhu, and X. Zhou, “Anti-dust: A method for identifying and preventing blockchain’s dust attacks,” in ICISCAE, 2018, pp. 274–280.

[54] H. Du, J. Liu, D. Niyato, J. Kang, Z. Xiong, J. Zhang, and D. I. Kim, “Attention-aware resource allocation and qoe analysis for metaverse xurllc services,” IEEE Journal on Selection Areas in Communications, accepted, 2023.

[55] The effects of lora on aigc product perceivable experience. 2023. [Online]. Available: <https://softwarekeep.com/help-center/ how-to-use-stable-diffusion-lora-models>

[56] E. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, “LoRA: Low-rank adaptation of large language models,” in International Conference on Learning Representations, 2022.

[57] Y. Wasa, K. Hirata, and K. Uchida, “A contract theory approach to dynamic incentive mechanism and control synthesis for moral hazard in power grids,” IEEE Transactions on Control Systems Technology, vol. 30, no. 5, pp. 2072–2083, 2022.

[58] C. Dai, K. Zhu, C. Yi, and E. Hossain, “Decoupled uplinkdownlink association in full-duplex cellular networks: A contracttheory approach,” IEEE Transactions on Mobile Computing, vol. 21, no. 3, pp. 911–925, 2022.

[59] H. Hasselt, “Double q-learning,” in Advances in Neural Information Processing Systems, vol. 23, 2010, pp. 2613–2621.