Trusted and Explainable AI for Secure Cloud and Edge Infrastructures

doi:10.23940/ijpe.26.11.p2.633643

Abstract

Abstract: Cloud and edge infrastructures now run the data and control loops of healthcare, smart cities, industry and finance, so one compromised node can disrupt an entire digital ecosystem. Protecting them requires intrusion detection that is accurate, privacy-preserving, resistant to manipulation and explainable. This paper addresses federated intrusion detection across cloud-coordinated edge sites, some of which may be compromised and poison the shared model. Existing federated detectors accept model updates on trust, while Byzantine-robust aggregation rules lose accuracy under the heterogeneous traffic of edge sites. Moreover, explainable AI serves mainly post-hoc analyst reports, and zero-trust access control and blockchain logging are seldom linked to learning. We propose XTrust-CE, whose core, Explanation-Fingerprint Trust Aggregation (EFTA), verifies each client update through the class-wise attribution fingerprint of the updated model on a verifier-owned reference set and through its reference behavior, admits only verified, clipped and reputation-weighted updates, and anchors trust scores in a PBFT-based ledger used by a risk-adaptive zero-trust policy. To the best of our knowledge, this is the first framework to use explanation fingerprints for federated update verification and couples that trust with zero-trust enforcement and tamper-evident logging. In a 20-site emulated testbed, EFTA preserved clean accuracy (96.71% versus 96.85% for FedAvg) and, with 40% poisoned sites, kept a 97.06% detection rate compared to 88.28% for Median and 85.03% for Trimmed Mean. Under targeted label flipping it quarantined every poisoned update, holding the ransomware and exfiltration miss rate at 3.52% (FedAvg 27.25%), while the zero-trust policy cut allowed evasive attack flows from 87.4% to 33.7%.

Key words: blockchain, Byzantine-robust aggregation, cloud security, edge computing, explainable artificial intelligence, federated learning, intrusion detection, zero trust architecture

Pawan Kumar Goel, Danish Ather, and Golnoosh Manteghi. Trusted and Explainable AI for Secure Cloud and Edge Infrastructures [J]. Int J Performability Eng, 2026, 22(11): 633-643.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Shi W., Cao J., Zhang Q., Li Y., andXu L., 2016. Edge computing: vision and challenges. IEEE Internet of Things Journal,3(5), pp. 637-646.
[2] Buczak A.L., andGuven E., 2015. A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Communications Surveys & Tutorials,18(2), pp. 1153-1176.
[3] POORNACHANDRAN P., AL-NEMRAT A.M.E.E.R., andVENKATRAMAN S., 2024. Deep learning approach for intelligent intrusion detection system.IEEE Access.
[4] Arrieta A.B., Díaz-Rodríguez N., Del Ser J., Bennetot A., Tabik S., Barbado A., García S., Gil-López S., Molina D., Benjamins R., andChatila R., 2020. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI.Information Fusion, 58, pp. 82-115.
[5] Ribeiro M.T., Singh S., andGuestrin C., 2016. " why should i trust you?" explaining the predictions of any classifier. InProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135-1144.
[6] Lundberg S.M., andLee S.I., 2017. A unified approach to interpreting model predictions.Advances in Neural Information Processing Systems, 30.
[7] McMahan B., Moore E., Ramage D., Hampson S., andy Arcas B.A., 2017. Communication-efficient learning of deep networks from decentralized data. InArtificial Intelligence and Statistics, pp. 1273-1282.
[8] Rose S., Borchert O., Mitchell S., andConnelly S., 2020. Zero trust architecture. NIST Special Publication,800(207), pp. 1-52.
[9] Syed N.F., Shah S.W., Shaghaghi A., Anwar A., Baig Z., andDoss R., 2022. Zero trust architecture (zta): A comprehensive survey.IEEE Access, 10, pp. 57143-57179.
[10] Shone N., Ngoc T.N., Phai V.D., andShi Q., 2018. A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence,2(1), pp. 41-50.
[11] Wang M., Zheng K., Yang Y., andWang X., 2020. An explainable machine learning framework for intrusion detection systems.IEEE Access, 8, pp. 73127-73141.
[12] Abou El Houda Z., Brik B., andKhoukhi L., 2022. “why should i trust your ids?”: an explainable deep learning framework for intrusion detection systems in internet of things networks.IEEE Open Journal of the Communications Society, 3, pp. 1164-1176.
[13] Fidel G., Bitton R., andShabtai A., 2020. When explainability meets adversarial learning: detecting adversarial examples using shap signatures. In2020 International Joint Conference on Neural Networks (IJCNN), pp. 1-8.
[14] Slack D., Hilgard S., Jia E., Singh S., andLakkaraju H., 2020. Fooling lime and shap: adversarial attacks on post hoc explanation methods. InProceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 180-186.
[15] Nguyen T.D., Marchal S., Miettinen M., Fereidooni H., Asokan N., andSadeghi A.R., 2019. DÏot: A federated self-learning anomaly detection system for IoT. In2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), pp. 756-767.
[16] Mothukuri V., Khare P., Parizi R.M., Pouriyeh S., Dehghantanha A., andSrivastava G., 2021. Federated-learning-based anomaly detection for IoT security attacks. IEEE Internet of Things Journal,9(4), pp. 2545-2554.
[17] Blanchard P., El Mhamdi E.M., Guerraoui R., andStainer J., 2017. Machine learning with adversaries: byzantine tolerant gradient descent.Advances in Neural Information Processing Systems, 30.
[18] Yin D., Chen Y., Kannan R., andBartlett P., 2018. Byzantine-robust distributed learning: towards optimal statistical rates. InInternational Conference on Machine Learning, pp. 5650-5659.
[19] Cao X., Fang M., Liu J., andGong N.Z., 2020. Fltrust: byzantine-robust federated learning via trust bootstrapping.Arxiv Preprint Arxiv:2012.13995.
[20] Moran Baruch G., andGoldberg Y., 2019. A little is enough: circumventing defenses for distributed learning.Advances in Neural Information Processing Systems, 32.
[21] Lu Y., Huang X., Dai Y., Maharjan S., andZhang Y., 2019. Blockchain and federated learning for privacy-preserved data sharing in industrial IoT. IEEE Transactions on Industrial Informatics,16(6), pp. 4177-4186.
[22] Sundararajan M., Taly A., andYan Q., 2017. Axiomatic attribution for deep networks. InInternational Conference on Machine Learning, pp. 3319-3328.
[23] Castro M., andLiskov B., 1999. Practical byzantine fault tolerance. In OsDI,99(1999), pp. 173-186.
[24] Mironov I.,2017. Rényi differential privacy. In2017 IEEE 30th Computer Security Foundations Symposium (CSF), pp. 263-275.
[25] Madry A., Makelov A., Schmidt L., Tsipras D., andVladu A., 2017. Towards deep learning models resistant to adversarial attacks.Arxiv Preprint Arxiv:1706.06083.