Adaptive Budgeted Replay for Risk-Aware Digital-Twin Release Validation in Multi-Tenant Zero Trust SASE Systems

Authors

  • Adrian Singh Department of Computer Science, Virginia Tech, USA

DOI:

https://doi.org/10.54097/vtj4pe96

Keywords:

Zero Trust, SASE, digital twin, release validation, risk-aware testing, CVaR, sequential replay

Abstract

Risk-aware digital-twin release validation must protect heterogeneous tenants without making every release pay the full stress-replay cost. We present adaptive budgeted replay (ABR), a three-stage extension of the five-obligation RA-DT certificate, which combines criticality-weighted and aggregate loss, tenant-scenario CVaR, worst-tenant missed-attack rate, and worst-scenario false-alarm rate. Fixed stopping bands triage release candidates after three or six scenarios; ambiguous candidates receive twelve. We execute five independently seeded synthetic experiments, with 189 mutated releases, eight tenants, and independently generated pre-release and holdout portfolios in each experiment (945 candidate evaluations total). Balanced nominal-first ABR evaluates 5.99 rather than 12 scenarios per candidate (50.1% fewer logical replays) and agrees with full RA-DT on all 945 decisions; conservative ABR also agrees throughout while evaluating 7.41 scenarios on average. Aggressive stopping saves 63.5% of replay work but changes ten decisions. A second, stress-diverse scenario order gives one balanced-policy disagreement, exposing a sensitivity to scenario order. The twin-to-holdout margin correlation (0.947–0.982) is consistent with that reported for RA-DT, so the certificate that ABR approximates retains its pre-release fidelity on this benchmark. Across runs, full RA-DT admits 16 unsafe releases among 113 passes under the independent synthetic holdout; ABR preserves these decisions rather than improving their deployment validity. Results characterize a reproducible replay-cost versus decision-fidelity trade-off, with scenario-level cost distinguished from measured latency and synthetic evidence distinguished from operational SASE telemetry.

Downloads

Download data is not yet available.

References

[1] Rose, S., Borchert, O., Mitchell, S., & Connelly, S. (2020). Zero trust architecture (NIST SP 800-207). https://doi.org/10.6028/NIST.SP.800-207 DOI: https://doi.org/10.6028/NIST.SP.800-207-draft2

[2] Syed, N. F., et al. (2022). Zero Trust Architecture (ZTA): A comprehensive survey. IEEE Access, 10, 57143–57179. https://doi.org/10.1109/ACCESS.2022.3174679 DOI: https://doi.org/10.1109/ACCESS.2022.3174679

[3] Ding, J., & Teng, D. (2026). A risk-aware digital twin framework for release-readiness validation of multi-tenant Zero Trust SASE systems. Transactions on Computer Science and Intelligent Systems Research, 13, 247–259. https://doi.org/10.62051/f19vvd53

[4] Moustafa, N., & Slay, J. (2015). UNSW-NB15: A comprehensive data set for network intrusion detection systems. In Proceedings of MilCIS (pp. 1–6). https://doi.org/10.1109/MilCIS.2015.7348942 DOI: https://doi.org/10.1109/MilCIS.2015.7348942

[5] Rockafellar, R. T., & Uryasev, S. (2000). Optimization of conditional value-at-risk. Journal of Risk, 2(3), 21–41. https://doi.org/10.21314/JOR.2000.038 DOI: https://doi.org/10.21314/JOR.2000.038

[6] Wang, J., Liu, J., Ge, Y., & Jiang, B. (2023). Risk-aware ensemble learning for credit default prediction under economic uncertainty. World Journal of Economics and Business Research, 1(1), 18–32. DOI: https://doi.org/10.61784/wjebr4124

[7] Fuller, A., Fan, Z., Day, C., & Barlow, C. (2020). Digital twin: Enabling technologies, challenges and open research. IEEE Access, 8, 108952–108971. https://doi.org/10.1109/ACCESS.2020.2998358 DOI: https://doi.org/10.1109/ACCESS.2020.2998358

[8] Chandramouli, R., & Butcher, Z. (2023). A Zero Trust architecture model for access control in cloud-native applications in multi-cloud environments (NIST SP 800-207A). https://doi.org/10.6028/NIST.SP.800-207A DOI: https://doi.org/10.6028/NIST.SP.800-207A

[9] Ward, R., & Beyer, B. (2014). BeyondCorp: A new approach to enterprise security. ;login:, 39(6), 6–11.

[10] Moubayed, A., Refaey, A., & Shami, A. (2019). Software-defined perimeter (SDP): State of the art secure solution for modern networks. IEEE Network, 33(5), 226–233. https://doi.org/10.1109/MNET.2019.1800324 DOI: https://doi.org/10.1109/MNET.2019.1800324

[11] Tao, F., & Zhang, M. (2017). Digital twin shop-floor: A new shop-floor paradigm towards smart manufacturing. IEEE Access, 5, 20418–20427. https://doi.org/10.1109/ACCESS.2017.2756069 DOI: https://doi.org/10.1109/ACCESS.2017.2756069

[12] Ke, G., et al. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems (Vol. 30).

[13] Zhou, F. (2026). Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders. Innovation and Technology Studies, 3(1), 27–41. DOI: https://doi.org/10.61784/its4027

[14] Ovadia, Y., et al. (2019). Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. In Advances in Neural Information Processing Systems (Vol. 32).

[15] Rabanser, S., Günnemann, S., & Lipton, Z. C. (2019). Failing loudly: An empirical study of methods for detecting dataset shift. In Advances in Neural Information Processing Systems (Vol. 32).

[16] Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of ICML (Vol. PMLR 70, pp. 1321–1330).

[17] Chen, J., Han, X., Zhang, X., & Yang, Y. (2023). Exact concept-level explanations for early detection of financial misstatements. Eurasia Journal of Science and Technology, 5(2), 34–48. DOI: https://doi.org/10.61784/ejst4162

[18] Jia, Y., & Harman, M. (2011). An analysis and survey of the development of mutation testing. IEEE Transactions on Software Engineering, 37(5), 649–678. https://doi.org/10.1109/TSE.2010.62 DOI: https://doi.org/10.1109/TSE.2010.62

[19] Kazemian, P., Varghese, G., & McKeown, N. (2012). Header space analysis: Static checking for networks. In Proceedings of NSDI (pp. 113–126).

[20] Khurshid, A., Zou, X., Zhou, W., Caesar, M., & Godfrey, P. B. (2013). VeriFlow: Verifying network-wide invariants in real time. In Proceedings of NSDI (pp. 15–27). DOI: https://doi.org/10.1145/2342441.2342452

[21] Mai, H., et al. (2011). Debugging the data plane with Anteater. In Proceedings of ACM SIGCOMM (pp. 290–301). https://doi.org/10.1145/2018436.2018470 DOI: https://doi.org/10.1145/2018436.2018470

[22] Efron, B., & Tibshirani, R. J. (1993). An introduction to the bootstrap. Chapman & Hall. DOI: https://doi.org/10.1007/978-1-4899-4541-9

[23] National Institute of Standards and Technology. (2012). Guide for conducting risk assessments (NIST SP 800-30 Rev. 1). https://doi.org/10.6028/NIST.SP.800-30r1 DOI: https://doi.org/10.6028/NIST.SP.800-30r1

[24] Moustafa, N., & Slay, J. (2016). The evaluation of network anomaly detection systems: Statistical analysis of the UNSW-NB15 data set and the comparison with the KDD99 data set. Information Security Journal, 25(1–3), 18–31. https://doi.org/10.1080/19393555.2015.1125974 DOI: https://doi.org/10.1080/19393555.2015.1125974

[25] DeCusatis, C., Liengtiraphan, P., Sager, A., & Pinelli, M. (2016). Implementing zero trust cloud networks with transport access control and first packet authentication. In Proceedings of IEEE SmartCloud (pp. 5–10). https://doi.org/10.1109/SmartCloud.2016.22 DOI: https://doi.org/10.1109/SmartCloud.2016.22

[26] Ding, J., et al. (2026). Game-Theoretic Cost-Sensitive Adversarial Training for Robust Cloud Intrusion Detection Against GAN-Based Evasion Attacks. Applied Sciences, 16, 3944. https://doi.org/10.3390/app16083944 DOI: https://doi.org/10.3390/app16083944

[27] Yue, X., & Zhu, R. (2024). An explainable hybrid machine learning framework for cash-flow-conditioned multi-horizon liquidity risk early warning: An SME-oriented benchmark study. World Journal of Management Science, 2(1), 63–72. DOI: https://doi.org/10.61784/wms4120

Downloads

Published

02-11-2026

Issue

Section

Articles

How to Cite

Singh, A. (2026). Adaptive Budgeted Replay for Risk-Aware Digital-Twin Release Validation in Multi-Tenant Zero Trust SASE Systems. Academic Journal of Applied Sciences, 3(2), 51-58. https://doi.org/10.54097/vtj4pe96