Abstract
Blockchains based on Proof-of-Work can maintain a distributed ledger with a high security guarantee but also lead to severe energy waste due to the useless hash calculation. Proof-of-Useful-Work (PoUW) mechanisms are alternatives, but finding hard puzzles with easy verification and useful results is challenging. Recent popular deep learning algorithms require large amount of computation resources due to the large-scale training datasets and the complexity of the models. The work of deep learning training is useful, and the model verification process is much shorter than its training process. Therefore, in this paper, we propose DLchain, a PoUW-based blockchain using deep learning training as the hard puzzle. Theoretical analysis shows that DLchain can achieve a security level comparable to existing PoW-based cryptocurrency when the miners’ best interest is to maximize their revenue. Notably, this is achieved without relying on common assumptions made in existing PoUW-based blockchain such as globally synchronized timestamps. Simulated experiments also show that the extra network delay caused by data transfer and the full nodes’ validation is acceptable.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ball, M., Rosen, A., Sabin, M., Vasudevan, P.N.: Proofs of useful work. IACR Cryptology ePrint Archive, 2017:203 (2017)
Bardenet, R., Brendel, M., Kégl, B., Sebag, M.: Collaborative hyperparameter tuning. In: ICML 2013, pp. 199–207 (2013)
Barinov, I.: Proof of Stake Decentralized Autonomous Organization
Bentov, I., Lee, C., Mizrahi, A., Rosenfeld, M.: Proof of activity: extending bitcoin’s proof of work via proof of stake. IACR Cryptology ePrint Archive 2014:452 (2014)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13(Feb), 281–305 (2012)
Chatterjee, K., Goharshady, A.K., Pourdamghani, A.: Hybrid mining: exploiting blockchain’s computational power for distributed problem solving. In: SAC 2019, pp. 374–381. ACM (2019)
Chenli, C., Li, B., Shi, Y., Jung, T.: Energy-recycling blockchain with proof-of-deep-learning. arXiv preprint arXiv:1902.03912 (2019)
“Fake Stake” Kernel Description, February 2019. https://bit.ly/2Txk146
Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121–2159 (2011)
Dziembowski, S., Eckey, L., Faust, S.: Fairswap: how to fairly exchange digital goods. In: ACM SIGSAC, pp. 967–984 (2018)
King, S.: Primecoin: Cryptocurrency with Prime Number Proof-of-work, vol. 1, p. 6, 7 July 2013
King, S., Nadal, S.: PPCoin: Peer-to-Peer Crypto-currency With Proof-of-Stake. Self-published paper, 19 August 2012
Li, B., Chenli, C., Xu, X., Jung, T., Shi, Y.: Exploiting computation power of blockchain for biomedical image segmentation. In: CVPR 2019 Workshops (2019)
Lopp, J.: Bitcoin timestamp security, July 2019. https://bit.ly/332n877
Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)
Nakamoto, S., et al.: Bitcoin: A Peer-to-Peer Electronic Cash System (2008)
Nxt whitepaper. https://nxtwiki.org/wiki/Whitepaper:Nxt, journal=Nxt
Ongaro, D., Ousterhout, J.: In search of an understandable consensus algorithm. In:U SENIX ATC, vol. 14, pp. 305–319 (2014)
O’donoghue, B., Candes, E.: Adaptive restart for accelerated gradient schemes. Found. Comput. Math. 15(3), 715–732 (2015)
Paritytech. paritytech/parity-ethereum, July 2019. https://github.com/paritytech/parity/wiki/Proof-of-Authority-Chains
Perkins, T.J.: Reinforcement learning for pomdps based on action values and stochastic optimization. In: AAAI/IAAI, pp. 199–204 (2002)
Polyak, B.T., Juditsky, A.B.: Acceleration of stochastic approximation by averaging. SIAM J. Control Optim. 30(4), 838–855 (1992)
Ramachandran, G.S., et al.: Trinity: a byzantine fault-tolerant distributed publish-subscribe system with immutable blockchain-based persistence. In: ICBC, pp. 227–235. IEEE (2019)
Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)
Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)
Rumelhart, D.E., Hinton, G.E., Williams, R.J., et al.: Learning representations by back-propagating errors. Cogn. Model. 5(3), 1 (1988)
Saleh, F.: Blockchain Without Waste: Proof-of-Stake. Available at SSRN 3183935 (2019)
Shoker, A.: Sustainable blockchain through proof of exercise. In: NCA, pp. 1–9. IEEE (2017)
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NIPS, pp. 2951–2959 (2012)
Tencent. Tencent/neuralnlp-neuralclassifier, April 2020
Nvidia gtx 970 vs titan v. https://bit.ly/3aFwVCQ
Wang, W., et al.: A survey on consensus mechanisms and mining strategy management in blockchain networks. IEEE Access 7, 22328–22370 (2019)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)
Young, S.R., Rose, D.C., Karnowski, T.P. Lim, S.-H., Patton, R.M.: Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: MLHPC 2015, p. 4. ACM (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chenli, C., Li, B., Jung, T. (2020). DLchain: Blockchain with Deep Learning as Proof-of-Useful-Work. In: Ferreira, J.E., Palanisamy, B., Ye, K., Kantamneni, S., Zhang, LJ. (eds) Services – SERVICES 2020. SERVICES 2020. Lecture Notes in Computer Science(), vol 12411. Springer, Cham. https://doi.org/10.1007/978-3-030-59595-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-59595-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59594-4
Online ISBN: 978-3-030-59595-1
eBook Packages: Computer ScienceComputer Science (R0)