Local Differential Privacy (LDP) is the de facto protocol for releasing time-series data under formal privacy guarantees. Existing LDP schemes typically add Laplace noise of equal scale at every time step, which tends to drown out the short discriminative patches a classifier depends on. DP-SoftShape spends ϵ unevenly across patches. An attention head scores each shape patch by its contribution to the class label and the Laplace scale at that patch is set in inverse proportion to the score, so noisier perturbation falls on flatter regions while the patches that actually carry the class signal stay close to the original embedding. A uniform-budget version of the same architecture loses most of this gain (Section 4). A Mixture-of-Experts refinement layer downstream recovers features that the noise still disturbs. On 20 UCR datasets at four privacy budgets, DP-SoftShape attains a mean accuracy of 0.722, against 0.565 for ROCKET and 0.553 for Arsenal under the same input-LDP setting.
- Open Access
- Article
DP-SoftShape: Adaptive Differential Privacy via Attention-Guided Sparsification for Time-Series Classification
- Baobing Zhang 1,*,
- Wanxin Sui 2,
- Maozhen Li 2,*
Author Information
Received: 25 Jan 2026 | Revised: 13 May 2026 | Accepted: 19 May 2026 | Published: 27 May 2026
Abstract
Keywords
differential privacy | time series classification | adaptive noise allocation | mixture-of-experts
References
- 1.
Ismail Fawaz, H.; Forestier, G.; Weber, J.; et al. Deep Learning for Time Series Classification: A Review. Data Min. Knowl. Discov. 2019, 33, 917–963.
- 2.
Fawaz, H.I. Deep Learning for Time Series Classification. arXiv 2020, arXiv:2010.00567.
- 3.
Bagnall, A.; Lines, J.; Bostrom, A.; et al. The Great Time Series Classification Bake Off: A Review and Experimental Evaluation of Recent Algorithmic Advances. Data Min. Knowl. Discov. 2017, 31, 606–660.
- 4.
Dau, H.A.; Bagnall, A.; Kamgar, K.; et al. The UCR Time Series Archive. IEEE/CAA J. Autom. Sin. 2019, 6, 1293–1305.
- 5.
Ismail Fawaz, H.; Lucas, B.; Forestier, G.; et al. Inceptiontime: Finding Alexnet for Time Series Classification. Data Min. Knowl. Discov. 2020, 34, 1936–1962.
- 6.
Dempster, A.; Petitjean, F.;Webb, G.I. ROCKET: Exceptionally Fast and Accurate Time Series Classification Using Random Convolutional Kernels. Data Min. Knowl. Discov. 2020, 34, 1454–1495.
- 7.
de Montjoye, Y.A.; Hidalgo, C.A.; Verleysen, M.; et al. Unique in the Crowd: The Privacy Bounds of Human Mobility. Sci. Rep. 2013, 3, 1376.
- 8.
Narayanan, A.; Shmatikov, V. Robust De-Anonymization of Large Sparse Datasets. In Proceedings of the 2008 IEEE Symposium on Security and Privacy (SP), Oakland, CA, USA, 18–21 May 2008; pp. 111–125.
- 9.
Shokri, R.; Stronati, M.; Song, C.; et al. Membership Inference Attacks Against Machine Learning Models. In Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA, 22–24 May 2017; pp. 3–18.
- 10.
Albrecht, J.P. How the GDPR Will Change the World. Eur. Data Prot. L. Rev. 2016, 2, 287–289.
- 11.
Voigt, P.; Von dem Bussche, A. The EU General Data Protection Regulation (GDPR), A Practical Guide, 1st ed.; Springer International Publishing: Cham, Switzerland, 2017.
- 12.
U.S. Department of Health and Human Services Summary of the HIPAA Privacy Rule; U.S. Department of Health and Human Services: Washington, DC, USA, 2003.
- 13.
Dwork, C.; Roth, A. The Algorithmic Foundations of Differential Privacy. Found. Trends Theor. Comput. Sci. 2014,
9, 211–487. - 14.
Erlingsson, U´ .; Pihur, V.; Korolova, A. Rappor: Randomized Aggregatable Privacy-Preserving Ordinal Response. In Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security, Scottsdale, AZ, USA, 3–7 November 2014; pp. 1054–1067.
- 15.
Kairouz, P.; McMahan, H.B.; Avent, B.; et al. Advances and Open Problems in Federated Learning. Found. Trends Mach. Learn. 2021, 14, 1–210.
- 16.
Warner, S.L. Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias. J. Am. Stat. Assoc. 1965, 60, 63–69.
- 17.
Mao, Y.; Ye, Q.; Wang, Q.; et al. Differential Privacy for Time Series: A Survey. IEEE Data Eng. Bull. 2024, 47, 67–92.
- 18.
Wang, Z.; Yan, W.; Oates, T. Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 14–19 May 2017; pp. 1578–1585.
- 19.
Vaswani, A.; Shazeer, N.; Parmar, N.; et al. Attention Is All You Need. In Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017.
- 20.
Shazeer, N.; Mirhoseini, A.; Maziarz, K.; et al. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. arXiv 2017, arXiv:1701.06538.
- 21.
Middlehurst, M.; Large, J.; Flynn, M.; et al. HIVE-COTE 2.0: A New Meta Ensemble for Time Series Classification. Mach. Learn. 2021, 110, 3211–3243.
- 22.
Deng, H.; Runger, G.; Tuv, E.; et al. A Time Series Forest for Classification and Feature Extraction. Inf. Sci. 2013, 239, 142–153.
- 23.
Ye, L.; Keogh, E. Time Series Shapelets: A New Primitive for Data Mining. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Paris, France, 28 June–1 July 2009; pp. 947–956.
- 24.
Arachchige, P.C.M.; Bertok, P.; Khalil, I.; et al. Local Differential Privacy for Deep Learning. IEEE Internet Things J. 2019, 7, 5827–5842.
- 25.
Ye, Q.; Hu, H.; Li, N.; et al. Beyond Value Perturbation: Local Differential Privacy in the Temporal Setting. In Proceedings of the IEEE INFOCOM 2021-IEEE Conference on Computer Communications, Vancouver, BC, Canada, 10–13 May 2021; pp. 1–10.
- 26.
Zhang, Y.; Ye, Q.; Chen, R.; et al. Trajectory Data Collection with Local Differential Privacy. arXiv 2023, arXiv:2307.09339.
- 27.
Ye, Q.; Hu, H.; Huang, K.; et al. Stateful Switch: Optimized Time Series Release with Local Differential Privacy. In Proceedings of the IEEE INFOCOM 2023-IEEE Conference on Computer Communications, New York, NY, USA, 17–20 May 2023; pp. 1–10.
- 28.
Fan, L.; Xiong, L. An Adaptive Approach to Real-Time Aggregate Monitoring with Differential Privacy. IEEE Trans. Knowl. Data Eng. 2013, 26, 2094–2106.
- 29.
Zhang, W.; Jiang, N.; Yang, S.; et al. Federated Transfer Learning for Remaining Useful Life Prediction in Prognostics with Data Privacy. Meas. Sci. Technol. 2025, 36, 076107.
- 30.
El Ouadrhiri, A.; Abdelhadi, A. Differential Privacy for Deep and Federated Learning: A Survey. IEEE Access 2022, 10, 22359–22380.
- 31.
Yang, X.; Wang, T.; Ren, X.; et al. Survey on Improving Data Utility in Differentially Private Sequential Data Publishing. IEEE Trans. Big Data 2017, 7, 729–749.
- 32.
Mu, S.; Lin, S. A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications. arXiv 2025, arXiv:2503.07137.
- 33.
Fedus, W.; Zoph, B.; Shazeer, N. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. J. Mach. Learn. Res. 2022, 23, 1–39.
- 34.
Riquelme, C.; Puigcerver, J.; Mustafa, B.; et al. Scaling Vision with Sparse Mixture of Experts. Adv. Neural Inf. Process. Syst. 2021, 34, 8583–8595.
- 35.
Du, N.; Huang, Y.; Dai, A.M.; et al. Glam: Efficient Scaling of Language Models with Mixture-of-Experts. In Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, USA; 17–23 July 2022; pp. 5547–5569.
- 36.
Liu, Z.; Luo, Y.; Li, B.; et al. Learning Soft Sparse Shapes for Efficient Time-Series Classification. arXiv 2025, arXiv:2505.06892.
- 37.
Rastogi, V.; Nath, S. Differentially Private Aggregation of Distributed Time-Series with Transformation and Encryption. In Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, Indianapolis, IN, USA, 6–10 June 2010; pp. 735–746.
- 38.
Papernot, N.; Song, S.; Mironov, I.; et al. Scalable Private Learning with PATE. In Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 30 April–3 May 2018.
- 39.
Abadi, M.; Chu, A.; Goodfellow, I.; et al. Deep Learning with Differential Privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS), Vienna, Austria, 24–28 October 2016; pp. 308–318.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com