A dynamic algorithm for trust inference based on double DQN in the internet of things

Abstract

The development of the Internet of Things (IoT) has brought great convenience to people. However, some information security problems such as privacy leakage are caused by communicating with risky users. It is a challenge to choose reliable users with which to interact in the IoT. Therefore, trust plays a crucial role in the IoT because trust may avoid some risks. Agents usually choose reliable users with high trust to maximize their own interests based on reinforcement learning. However, trust propagation is time-consuming, and trust changes with the interaction process in social networks. To track the dynamic changes in trust values, a dynamic trust inference algorithm named Dynamic Double DQN Trust (Dy-DDQNTrust) is proposed to predict the indirect trust values of two users without direct contact with each other. The proposed algorithm simulates the interactions among users by double DQN. Firstly, CurrentNet and TargetNet networks are used to select users for interaction. The users with high trust are chosen to interact in future iterations. Secondly, the trust value is updated dynamically until a reliable trust path is found according to the result of the interaction. Finally, the trust value between indirect users is inferred by aggregating the opinions from multiple users through a Modified Collaborative Filtering Average-based Similarity (SMCFAvg) aggregation strategy. Experiments are carried out on the FilmTrust and the Epinions datasets. Compared with TidalTrust, MoleTrust, DDQNTrust, DyTrust and Dynamic Weighted Heuristic trust path Search algorithm (DWHS), our dynamic trust inference algorithm has higher prediction accuracy and better scalability.

Keywords

Internet of things / Information security / Reinforcement learning / Trust propagation / Trust inference

References

[1] R. Faqihi, J. Ramakrishnan, D. Mavaluru,An evolutionary study on the threats, trust, security, and challenges in siot (social internet of things), Mater. Today Proc. https://doi.org/10.1016/j.matpr.2020.09.618.

[2] H. Lin, S. Garg, J. Hu, X. Wang, M.J. Piran, M.S. Hossain, Data fusion and transfer learning empowered granular trust evaluation for internet of things, Inf. Fusion 78 (2022) 149-157.

[3] Y. Yi, Z. Zhang, L. T. Yang, X. Wang, C. Gan, Edge-aided control dynamics for information diffusion in social internet of things, Neurocomputing. https://doi.org/10.1016/j.neucom.2021.03.140.

[4] V. Mohammadi, A.M. Rahmani, A. Darwesh, A. Sahafi, Trust-based friend selection algorithm for navigability in social internet of things, Knowl. Base Syst. 232 (2021) 107479.

[5] J. Golbeck, Generating Predictive Movie Recommendations from Trust in Social Networks, Springer, Berlin, Heidelberg. https://doi.org/10.1007/11755593_8.

[6] P. Massa, P. Avesani, Trust metrics on controversial users: balancing between tyranny of the majority, Int. J. Semantic Web Inf. Syst. 3 (1) (2007) 39-64.

[7] M. Ghavipour, M.R. Meybodi, Trust propagation algorithm based on learning automata for inferring local trust in online social networks, Knowl. Base Syst. 143 (2018) 307-316.

[8] H. Fang, X. Li, J. Zhang, Integrating social influence modeling and user modeling for trust prediction in signed networks, Artif. Intell. 302 (2022) 103628.

[9] R. Kumar, R. Sharma, Leveraging blockchain for ensuring trust in iot: a survey, J. King Saud University-Comput. Inform. Sci. https://doi.org/10.1016/j.jksuci.2021.09.004.

[10] W. Meng, W. Li, L. Zhu, Enhancing medical smartphone networks via blockchain-based trust management against insider attacks, IEEE Trans. Eng. Manag. 67 (4)(2020) 1377-1386.

[11] D. Jelenc, L.H. Tamargo, S. Gottifredi, A.J. García, Credibility dynamics: a belief-revision-based trust model with pairwise comparisons, Artif. Intell. 293 (2021) 103450.

[12] Y. Zhang, X. Chen, L. Gao, Y. Dong, W. Pedryczc, Consensus reaching with trust evolution in social network group decision making, Expert Syst. Appl. 188 (2022) 116022.

[13] Z. Xu, X. Li, W. Xiong, Q. Lin, J. Mao, A dynamic multi-dimension trust model for information service quality evaluation, Procedia Comput. Sci. 187 (2021) 601-606.

[14] M. Ghavipour, M.R. Meybodi, A dynamic algorithm for stochastic trust propagation in online social networks: learning automata approach, Comput. Commun. 123 (2018) 11-23.

[15] J. Jiang, H. Wang, W. Li, A trust model based on a time decay factor for use in social networks, Comput. Electr. Eng. 85 (2020) 106706.

[16] G. Abirami, R. Venkataraman, Performance analysis of the dynamic trust model algorithm using the fuzzy inference system for access control, Comput. Electr. Eng. 92 (2021) 107132.

[17] X. Molinero, F. Riquelme, Influence decision models: from cooperative game theory to social network analysis, Computer Sci. Rev. 39 (2021) 100343.

[18] T. Zhao, H.V. Zhao, I. King, Exploiting game theoretic analysis for link recommendation in social networks, in: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Association for Computing Machinery, New York, NY, USA, 2015, pp. 851-860.

[19] R. Sutton, A. Barto, Reinforcement learning:an introduction, Reinforcement Learning:An Introduction (1998).

[20] S. Liu, X. Tong, Urban transportation path planning based on reinforcement learning, J. Comput. Appl. 41 (2021) 185-190.

[21] F. Qi, X. Tong, L. Yu, Agent trust boost via reinforcement learning dqn, J. Comput. Res. Dev. 57 (6) (2020) 1227.

[22] Y.A. Kim, H.S. Song, Strategies for predicting local trust based on trust propagation in social networks, Knowl. Base Syst. 24 (8) (2011) 1360-1371.

[23] Y. Ruan, A. Durresi, A survey of trust management systems for online social communities-trust modeling, trust inference and attacks, Knowl. Base Syst. (2016) 150-163, https://doi.org/10.1016/j.knosys.2016.05.042.

[24] J.A. Golbeck,Computing and Applying Trust in Web-Based Social Networks, Ph.D. thesis, University of Maryland, College Park, 2005, http://hdl.handle.net/1903/2384.

[25] J.-H. Cho, K. Chan, S. Adali, A survey on trust modeling, ACM Comput. Surv. 48 (2). https://doi.org/10.1145/2815595.

[26] D. Mandaglio, A. Tagarelli, Generalized preference learning for trust network inference, IEEE Access 7 (2019) 174583-174596.

[27] Y. Wang, X. Tong, Trust prediction based on extreme learning machine and asymmetric tri-training, IEEE Access 9 (2021) 64358-64367.

[28] Y. Qiao, Q. Lan, Z. Zhou, C. Ma, Privacy-preserving credit evaluation system based on blockchain, Expert Syst. Appl. 188 (2022) 115989.

[29] X. Tong, W. Zhang, Y. Long, Transitivity of agent subjective trust, J. Softw. 23 (11)(2012) 2862-2870.

[30] L. Xiong, L. Liu, Peertrust: supporting reputation-based trust for peer-to-peer electronic communities, IEEE Trans. Knowl. Data Eng. 16 (7) (2004) 843-857.

[31] K. Akilal, M. Omar, H. Slimani, Characterizing and using gullibility, competence, and reciprocity in a very fast and robust trust and distrust inference algorithm for weighted signed social networks, Knowl. Base Syst. 192 (2020) 105345.

[32] H. Xia, Z. Li, Y. Zheng, A. Liu, Y.-J. Choi, H. Sekiya, A novel light-weight subjective trust inference framework in manets, IEEE Transact. Sustain. Computing 5 (2) (2020) 236-248.

[33] F. Völter, N. Urbach, J. Padget, Trusting the trust machine: evaluating trust signals of blockchain applications, Int. J. Inf. Manag. (2021) 102429, https://doi.org/10.1016/j.ijinfomgt.2021.102429.

[34] S. Pal, A. Hill, T. Rabehaja, M. Hitchens, A blockchain-based trust management framework with verifiable interactions, Comput. Network. 200 (2021) 108506.

[35] Y. Xu, Z. Gong, J.Y.-L. Forrest, E. Herrera-Viedma, Trust propagation and trust network evaluation in social networks based on uncertainty theory, Knowl. Base Syst. 234 (2021) 107610.

[36] R. Kong, X. Tong, Dynamic weighted heuristic trust path search algorithm, IEEE Access 8 (2020) 157382-157390.

[37] W. Jiang, J. Wu, F. Li, G. Wang, H. Zheng, Trust evaluation in online social networks using generalized network flow, IEEE Trans. Comput. 65 (3) (2016) 952-963.

[38] B. Cai, X. Li, Y. Gao,An efficient trust inference algorithm with local weighted centrality for social recommendation, in: ICC 2020-2020 IEEE International Conference on Communications, ICC, 2020, pp. 1-6.

[39] B. Cai, X. Li, W. Kong, J. Yuan, S. Yu, A reliable and lightweight trust inference model for service recommendation in siot, IEEE Internet Things J. (2021), 1-1. https://doi.org/10.1109/JIOT.2021.3125347.

[40] W. Jiang, G. Wang, W. Jie, Generating trusted graphs for trust evaluation in online social networks, Future Generat. Comput. Syst. 31 (feb.) (2014) 48-58, https://doi.org/10.1016/j.future.2012.06.010.

[41] X. Chen, Y. Yuan, M.A. Orgun, L. Lu, A topic-sensitive trust evaluation approach for users in online communities, Knowl. Base Syst. 194 (2020) 105546.

[42] C. Perez, B. Birregah, M. Lemercier, A smartphone-based online social network trust evaluation system, Social Network Analys. Mining 3 (4) (2013) 1293-1310.

[43] C. Mao, C. Xu, Q. He, A cost-effective algorithm for inferring the trust between two individuals in social networks, Knowl. Base Syst. 164 (2019) 122-138.

[44] X. Tong, H. Huang, W. Zhang, Prediction and abnormal behavior detection of agent dynamie interaction trust, J. Comput. Res. Dev. 8 (46) (2009) 1364-1370.

[45] J. You, J. Shangguan, L. Zhuang, N. Li, Y. Wang, An autonomous dynamic trust management system with uncertainty analysis, Knowl. Base Syst. 161 (2018) 101-110.

[46] C. Watkins, P. Dayan, Q-learning, Machine Learning 8 (3-4) (1992) 279-292.

[47] M. Volodymyr, K. Koray, S. David, A.A. Rusu, V. Joel, M.G. Bellemare, G. Alex, R. Martin, A.K. Fidjeland, O.a. Georg, Human-level control through deep reinforcement learning, Nature 518 (7540) (2015) 529-533.

[48] H. V. Hasselt, A. Guez, D. Silver, Deep reinforcement learning with double q-learning, Computer ence. URL https://arxiv.org/abs/1509.06461.

[49] Y. Ren, W. Liu, A. Liu, T. Wang, A. Li, A privacy-protected intelligent crowdsourcing application of iot based on the reinforcement learning, Future Generat. Comput. Syst. 127 (2022) 56-69.

[50] X. Zhuang, X. Tong, A local trust inferring algorithm based on reinforcement learning doubledqn in online social networks, in: 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI, 2020, pp. 1064-1069.