Page 369 - 《软件学报》2026年第6期

2688 软件学报 2026 年第 37 卷第 6 期

强推荐系统的鲁棒性. 其次, 设计基于扩散模型的可信用户生成算法, 通过迭代去噪的方式深入学习并模拟真实用
户的行为特征和数据分布, 生成高质量的可信用户数据. 此外, 在真实的 WS-DREAM 响应时间数据集上对 11 种
推荐算法进行实验, 并从混合攻击、防御规模和防御强度等多维度进行分析. 结果表明, 本文提出的基于可信数据
增强的投毒攻击持续防御方法能够有效降低投毒攻击的影响. 未来工作将聚焦于优化可信用户生成算法, 为云
API 推荐系统提供更优质的训练数据, 进一步提升推荐算法的鲁棒性.

References
[1] Chen Z, Pan MS, He PF, Qi WC, Liu LL, Shen LM, You DL. Context and auto-interaction are all you need: Towards context embedding
based QoS prediction via automatic feature interaction for high quality cloud API delivery. Future Generation Computer Systems, 2022,
128: 265–281. [doi: 10.1016/j.future.2021.10.014]
[2] Gong WW, Zhang XY, Chen YF, He Q, Beheshti A, Xu XL, Yan C, Qi LY. DAWAR: Diversity-aware Web APIs recommendation for
mashup creation based on correlation graph. In: Proc. of the 45th Int’l ACM SIGIR Conf. on Research and Development in Information
Retrieval. Madrid: ACM, 2022. 395–404. [doi: 10.1145/3477495.3531962]
[3] Gamez-Diaz A, Fernandez P, Ruiz-Cortés A. Governify for APIs: SLA-driven ecosystem for API governance. In: Proc. of the 27th ACM
Joint Meeting on European Software Engineering Conf. and Symp. on the Foundations of Software Engineering. Tallinn: ACM, 2019.
1120–1123. [doi: 10.1145/3338906.3341176]
[4] Gartner. Gartner magic quadrant for full life cycle API management. 2021. https://www.gartner.com/en/documents/4006268
[5] He Q, Zhou R, Zhang XY, Wang YC, Ye DY, Chen FF, Chen SP, Grundy J, Yang Y. Efficient keyword search for building service-based
systems based on dynamic programming. In: Proc. of the 15th Int’l Conf. on Service-oriented Computing. Malaga: Springer, 2017.
462–470. [doi: 10.1007/978-3-319-69035-3_33]
[6] Cao BQ, Liu JX, Wen YP, Li HT, Xiao QX, Chen JJ. QoS-aware service recommendation based on relational topic model and
factorization machines for IoT mashup applications. Journal of Parallel and Distributed Computing, 2019, 132: 177–189. [doi: 10.1016/j.
jpdc.2018.04.002]
[7] Bermbach D, Wittern E. Benchmarking Web API quality-revisited. Journal of Web Engineering, 2020, 19(5–6): 603–646. [doi: 10.13052/
jwe1540-9589.19563]
[8] Zhang YW, Xiang T, Guo X, Jia ZH, He Q. Quality prediction for services based on SOM neural network. Ruan Jian Xue Bao/Journal of
Software, 2018, 29(11): 3388–3399 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/5474.htm [doi: 10.13328/j.cnki.
jos.005474]
[9] Zheng ZB, Li XL, Tang MD, Xie FF, Lyu MR. Web service QoS prediction via collaborative filtering: A survey. IEEE Trans. on Services
Computing, 2022, 15(4): 2455–2472. [doi: 10.1109/TSC.2020.2995571]
[10] Chen Z, Shen LM, Li F. Exploiting Web service geographical neighborhood for collaborative QoS prediction. Future Generation
Computer Systems, 2017, 68: 248–259. [doi: 10.1016/j.future.2016.09.022]
[11] Hussain W, Merigó JM, Raza MR, Gao HH. A new QoS prediction model using hybrid IOWA-ANFIS with fuzzy C-means, subtractive
clustering and grid partitioning. Information Sciences, 2022, 584: 280–300. [doi: 10.1016/j.ins.2021.10.054]
[12] Chen Z, Bao TY, Qi WC, You DL, Liu LL, Shen LM. Poisoning QoS-aware cloud API recommender system with generative adversarial
network attack. Expert Systems with Applications, 2024, 238: 121630. [doi: 10.1016/j.eswa.2023.121630]
[13] Xing XY, Meng W, Doozan D, Snoeren AC, Feamster N, Lee W. Take this personally: Pollution attacks on personalized services. In:
Proc. of the 22nd USENIX Conf. on Security. Washington: USENIX Association, 2013. 671–686.
[14] Yang F, Gao M, Yu JL, Song YQ, Wang XY. Detection of shilling attack based on Bayesian model and user embedding. In: Proc. of the
30th IEEE Int’l Conf. on Tools with Artificial Intelligence. Volos: IEEE, 2018. 639–646. [doi: 10.1109/ICTAI.2018.00102]
[15] Mehta B, Nejdl W. Unsupervised strategies for shilling detection and robust collaborative filtering. User Modeling and User-adapted
Interaction, 2009, 19(1–2): 65–97. [doi: 10.1007/s11257-008-9050-4]
[16] Wu ZA, Wu JJ, Cao J, Tao DC. HySAD: A semi-supervised hybrid shilling attack detector for trustworthy product recommendation. In:
Proc. of the 18th ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining. Beijing: ACM, 2012. 985–993. [doi: 10.1145/
2339530.2339684]
[17] Lin C, Chen S, Li H, Xiao YH, Li LY, Yang Q. Attacking recommender systems with augmented user profiles. In: Proc. of the 29th ACM
Int’l Conf. on Information & Knowledge Management. New York: ACM, 2020. 855–864. [doi: 10.1145/3340531.3411884]