{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:46:58Z","timestamp":1783000018288,"version":"3.54.5"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T00:00:00Z","timestamp":1722988800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T00:00:00Z","timestamp":1722988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["NWA.1215.18.014"],"award-info":[{"award-number":["NWA.1215.18.014"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Netherlands Organisation for Scientific Research","award":["CS.019"],"award-info":[{"award-number":["CS.019"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cryptogr Eng"],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Despite considerable achievements of deep learning-based side-channel analysis, overfitting represents a significant obstacle in finding optimized neural network models. This issue is not unique to the side-channel domain. Regularization techniques are popular solutions to overfitting and have long been used in various domains. At the same time, the works in the side-channel domain show sporadic utilization of regularization techniques. What is more, no systematic study investigates these techniques\u2019 effectiveness. In this paper, we aim to investigate the regularization effectiveness on a randomly selected model, by applying 4 powerful and easy-to-use regularization techniques to 8 combinations of datasets, leakage models, and deep learning topologies. The investigated techniques are\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$L_1$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:msub>\n                            <mml:mi>L<\/mml:mi>\n                            <mml:mn>1<\/mml:mn>\n                          <\/mml:msub>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    ,\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$L_2$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:msub>\n                            <mml:mi>L<\/mml:mi>\n                            <mml:mn>2<\/mml:mn>\n                          <\/mml:msub>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    , dropout, and early stopping. Our results show that while all these techniques can improve performance in many cases,\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$L_1$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:msub>\n                            <mml:mi>L<\/mml:mi>\n                            <mml:mn>1<\/mml:mn>\n                          <\/mml:msub>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    and\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:tex-math>$$L_2$$<\/jats:tex-math>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <mml:msub>\n                            <mml:mi>L<\/mml:mi>\n                            <mml:mn>2<\/mml:mn>\n                          <\/mml:msub>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    are the most effective. Finally, if training time matters, early stopping is the best technique.\n                  <\/jats:p>","DOI":"10.1007\/s13389-024-00361-5","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T13:02:49Z","timestamp":1723035769000},"page":"609-629","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Regularizers to the rescue: fighting overfitting in deep learning-based side-channel analysis"],"prefix":"10.1007","volume":"14","author":[{"given":"Azade","family":"Rezaeezade","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lejla","family":"Batina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,7]]},"reference":[{"key":"361_CR1","doi-asserted-by":"crossref","unstructured":"Kocher, P.\u00a0C., Jaffe, J., Jun, B.: Differential power analysis. In: M.\u00a0J. Wiener, editor, Advances in Cryptology - CRYPTO \u201999, 19th Annual International Cryptology Conference, Santa Barbara, California, USA, August 15-19, 1999, Proceedings, Lecture Notes in Computer Science, vol. 1666, pp. 388\u2013397. Springer, (1999)","DOI":"10.1007\/3-540-48405-1_25"},{"key":"361_CR2","doi-asserted-by":"crossref","unstructured":"Quisquater, J., Samyde, D.: Electromagnetic analysis (EMA): measures and counter-measures for smart cards. In: I.\u00a0Attali and T.\u00a0P. Jensen, editors, Smart Card Programming and Security, International Conference on Research in Smart Cards, E-smart 2001, Cannes, France, September 19-21, 2001, Proceedings, Lecture Notes in Computer Science, vol. 2140, pp. 200\u2013210. Springer, (2001)","DOI":"10.1007\/3-540-45418-7_17"},{"key":"361_CR3","volume-title":"Power analysis attacks - revealing the secrets of smart cards","author":"S Mangard","year":"2007","unstructured":"Mangard, S., Oswald, E., Popp, T.: Power analysis attacks - revealing the secrets of smart cards. Springer, Berlin (2007)"},{"key":"361_CR4","doi-asserted-by":"crossref","unstructured":"Picek, S., Heuser, A., Perin, G., Guilley, S.: Profiled side-channel analysis in the efficient attacker framework. In: Grosso V. and T.\u00a0P\u00f6ppelmann, (eds.) Smart Card Research and Advanced Applications - 20th International Conference, CARDIS 2021, L\u00fcbeck, Germany, November 11-12, 2021, Revised Selected Papers, Lecture Notes in Computer Science, vol. 13173, pp. 44\u201363. Springer, (2021)","DOI":"10.1007\/978-3-030-97348-3_3"},{"key":"361_CR5","doi-asserted-by":"crossref","unstructured":"Chari, S., Rao, J.\u00a0R., Rohatgi, P.: Template attacks. In: B.\u00a0S.\u00a0K. Jr., \u00c7.\u00a0K. Ko\u00e7, and Paar C. (eds.) Cryptographic Hardware and Embedded Systems - CHES 2002, 4th International Workshop, Redwood Shores, CA, USA, August 13-15, 2002, Revised Papers, Lecture Notes in Computer Science, vol. 2523, pp. 13\u201328. Springer, (2002)","DOI":"10.1007\/3-540-36400-5_3"},{"key":"361_CR6","doi-asserted-by":"crossref","unstructured":"Brier, E., Clavier, C., Olivier, F.: Correlation power analysis with a leakage model. In: Joye M. and Quisquater J. (eds.), Cryptographic Hardware and Embedded Systems - CHES 2004: 6th International Workshop Cambridge, MA, USA, August 11-13, 2004. Proceedings, Lecture Notes in Computer Science, vol. 3156, pp. 16\u201329. Springer, (2004)","DOI":"10.1007\/978-3-540-28632-5_2"},{"key":"361_CR7","doi-asserted-by":"crossref","unstructured":"Gierlichs, B., Batina, L., Tuyls, P., Preneel, B.: Mutual information analysis. In: Oswald E. and Rohatgi P. (eds.) Cryptographic Hardware and Embedded Systems - CHES 2008, 10th International Workshop, Washington, D.C., USA, August 10-13, 2008. Proceedings, Lecture Notes in Computer Science, vol. 5154, pp. 426\u2013442. Springer, (2008)","DOI":"10.1007\/978-3-540-85053-3_27"},{"issue":"2","key":"361_CR8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s13389-014-0089-3","volume":"5","author":"L Lerman","year":"2015","unstructured":"Lerman, L., Bontempi, G., Markowitch, O.: A machine learning approach against a masked AES: reaching the limit of side-channel attacks with a learning model. J. Cryptogr. Eng. 5(2), 123\u2013139 (2015)","journal-title":"J. Cryptogr. Eng."},{"key":"361_CR9","doi-asserted-by":"crossref","unstructured":"Picek, S., Heuser, A., Jovic, A., Ludwig, S.\u00a0A., Guilley, S., Jakobovic, D., Mentens, N.: Side-channel analysis and machine learning: A practical perspective. In: 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, AK, USA, May 14-19, 2017, pp. 4095\u20134102. IEEE, (2017)","DOI":"10.1109\/IJCNN.2017.7966373"},{"key":"361_CR10","unstructured":"Heuser, A., Zohner, M.: Intelligent machine homicide - breaking cryptographic devices using support vector machines. In: Schindler W. and Huss S.\u00a0A. (eds.) Constructive Side-Channel Analysis and Secure Design - Third International Workshop, COSADE 2012, Darmstadt, Germany, May 3-4, 2012. Proceedings, Lecture Notes in Computer Science, vol. 7275, pp.249\u2013264. Springer, (2012)"},{"key":"361_CR11","doi-asserted-by":"crossref","unstructured":"Cagli, E., Dumas, C., Prouff, E.: Convolutional neural networks with data augmentation against jitter-based countermeasures - profiling attacks without pre-processing. In: Fischer W. and Homma N. (eds.) Cryptographic Hardware and Embedded Systems - CHES 2017 - 19th International Conference, Taipei, Taiwan, September 25-28, 2017, Proceedings, Lecture Notes in Computer Science, vol. 10529, pp.45\u201368. Springer, (2017)","DOI":"10.1007\/978-3-319-66787-4_3"},{"issue":"3","key":"361_CR12","doi-asserted-by":"publisher","first-page":"148","DOI":"10.46586\/tches.v2019.i3.148-179","volume":"2019","author":"J Kim","year":"2019","unstructured":"Kim, J., Picek, S., Heuser, A., Bhasin, S., Hanjalic, A.: Make some noise. unleashing the power of convolutional neural networks for profiled side-channel analysis. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2019(3), 148\u2013179 (2019)","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"361_CR13","doi-asserted-by":"crossref","unstructured":"Picek, S., Perin, G., Mariot, L., Wu, L., Batina, L.: Sok: Deep learning-based physical side-channel analysis. ACM Comput. Surv. oct 2022. Just Accepted","DOI":"10.1145\/3569577"},{"key":"361_CR14","unstructured":"Ramezanpour, K., Abdulgadir, A., Diehl, W., Kaps, J.-P., Ampadu., P.: Active and passive side-channel key recovery attacks on ascon. In:Proc. NIST Lightweight Cryptogr. Workshop, pp. 1\u201327, (2020)"},{"key":"361_CR15","doi-asserted-by":"crossref","unstructured":"Luo, S., Wu, W., Li, Y., Zhang, R., Liu, Z.: An efficient soft analytical side-channel attack on ascon. In: International Conference on Wireless Algorithms, Systems, and Applications, pp. 389\u2013400. Springer, 2022","DOI":"10.1007\/978-3-031-19208-1_32"},{"key":"361_CR16","unstructured":"Ramezanpour, K., Ampadu, P., Diehl, W.: Scarl: side-channel analysis with reinforcement learning on the ascon authenticated cipher. arXiv preprint arXiv:2006.03995, (2020)"},{"key":"361_CR17","doi-asserted-by":"crossref","unstructured":"Shanmugam, D., Schaumont, P.: Improving side-channel leakage assessment using pre-silicon leakage models. In: International Workshop on Constructive Side-Channel Analysis and Secure Design, pp. 105\u2013124. Springer, (2023)","DOI":"10.1007\/978-3-031-29497-6_6"},{"issue":"3","key":"361_CR18","doi-asserted-by":"publisher","first-page":"677","DOI":"10.46586\/tches.v2021.i3.677-707","volume":"2021","author":"J Rijsdijk","year":"2021","unstructured":"Rijsdijk, J., Wu, L., Perin, G., Picek, S.: Reinforcement learning for hyperparameter tuning in deep learning-based side-channel analysis. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2021(3), 677\u2013707 (2021)","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"361_CR19","unstructured":"Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning Adaptive computation and machine learning. MIT Press, (2016)"},{"key":"361_CR20","unstructured":"G\u00e9ron, A.: Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O\u2019Reilly Media, Inc., (2022)"},{"key":"361_CR21","unstructured":"Krogh, A., Hertz, J.\u00a0A.: A simple weight decay can improve generalization. In: Moody J.\u00a0E., HansonS.\u00a0J. and Lippmann R., (eds.) Advances in Neural Information Processing Systems 4, [NIPS Conference, Denver, Colorado, USA, December 2-5, 1991], pp. 950\u2013957. Morgan Kaufmann, (1991)"},{"issue":"1","key":"361_CR22","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"361_CR23","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pp. 648\u2013656. IEEE Computer Society, (2015)","DOI":"10.1109\/CVPR.2015.7298664"},{"issue":"1","key":"361_CR24","first-page":"1","volume":"2020","author":"G Zaid","year":"2020","unstructured":"Zaid, G., Bossuet, L., Habrard, A., Venelli, A.: Methodology for efficient CNN architectures in profiling attacks. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2020(1), 1\u201336 (2020)","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"361_CR25","doi-asserted-by":"crossref","unstructured":"Perin, G., Buhan, I., Picek, S.: Learning when to stop: A mutual information approach to prevent overfitting in profiled side-channel analysis. In: Bhasin S. and Santis F.\u00a0D., (eds.) Constructive Side-Channel Analysis and Secure Design - 12th International Workshop, COSADE 2021, Lugano, Switzerland, October 25-27, 2021, Proceedings, Lecture Notes in Computer Science, vol. 12910, pp.53\u201381. Springer, (2021)","DOI":"10.1007\/978-3-030-89915-8_3"},{"key":"361_CR26","doi-asserted-by":"crossref","unstructured":"Robissout, D., Zaid, G., Colombier, B., Bossuet, L., Habrard, A. Online performance evaluation of deep learning networks for profiled side-channel analysis. In: Bertoni G.M. and Regazzoni F.(eds.), Constructive Side-Channel Analysis and Secure Design 11th International Workshop, OSADE2020, Lugano, Switzerland, April1-3,2020,Revised Selected Papers,Lecture Notes in Computer Science, vol. 12244, pp. 200\u2013218. Springer, (2020)","DOI":"10.1007\/978-3-030-68773-1_10"},{"key":"361_CR27","doi-asserted-by":"crossref","unstructured":"Rezaeezade, A., Perin, G., Picek, S.: To overfit, or not to overfit: improving the performance of deep learning-based sca. In:International Conference on Cryptology in Africa, pp. 397\u2013421. Springer, (2022)","DOI":"10.1007\/978-3-031-17433-9_17"},{"issue":"4","key":"361_CR28","doi-asserted-by":"publisher","first-page":"337","DOI":"10.46586\/tches.v2020.i4.337-364","volume":"2020","author":"G Perin","year":"2020","unstructured":"Perin, G., Chmielewski, L., Picek, S.: Strength in numbers: Improving generalization with ensembles in machine learning-based profiled side-channel analysis. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2020(4), 337\u2013364 (2020)","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"361_CR29","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Bach F.R. and Blei D.\u00a0M., (eds.)Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, vol. 37 of JMLR Workshop and Conference Proceedings, pages 448\u2013456. JMLR.org, 2015"},{"issue":"1","key":"361_CR30","first-page":"348","volume":"2020","author":"L Masure","year":"2020","unstructured":"Masure, L., Dumas, C., Prouff, E.: A comprehensive study of deep learning for side-channel analysis. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2020(1), 348\u2013375 (2020)","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"361_CR31","unstructured":"Prouff, E., Strullu, R., Benadjila, R., Cagli, E., Dumas, C. Study of deep learning techniques for side-channel analysis and introduction to ASCAD database. IACR Cryptol. ePrint Arch., page\u00a053, (2018)"},{"key":"361_CR32","unstructured":"Agence nationale de la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019information (ANSSI). ASCAD. Github repository, (2018). https:\/\/github.com\/ANSSI-FR\/ASCAD"},{"key":"361_CR33","doi-asserted-by":"crossref","unstructured":"Perin, G., Picek, S.: On the influence of optimizers in deep learning-based side-channel analysis. In: Dunkelman O., M.\u00a0J.\u00a0J. Jr., and O\u2019Flynn C., (eds.), Selected Areas in Cryptography - SAC 2020 - 27th International Conference, Halifax, NS, Canada (Virtual Event), October 21-23, 2020, Revised Selected Papers, Lecture Notes in Computer Science, vol. 12804, pp. 615\u2013636. Springer, (2020)","DOI":"10.1007\/978-3-030-81652-0_24"},{"issue":"19\u201320","key":"361_CR34","doi-asserted-by":"publisher","first-page":"12777","DOI":"10.1007\/s11042-019-08453-9","volume":"79","author":"C Garbin","year":"2020","unstructured":"Garbin, C., Zhu, X., Marques, O.: Dropout vs. batch normalization: an empirical study of their impact to deep learning. Multim. Tools Appl. 79(19\u201320), 12777\u201312815 (2020)","journal-title":"Multim. Tools Appl."},{"key":"361_CR35","doi-asserted-by":"crossref","unstructured":"Li, X., Chen, S., Hu, X., Yang, J.: Understanding the disharmony between dropout and batch normalization by variance shift. In:IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 2682\u20132690. Computer Vision Foundation\/IEEE, (2019)","DOI":"10.1109\/CVPR.2019.00279"},{"key":"361_CR36","unstructured":"Arora, S., Cohen, N., Hu, W., Luo, Y.: Implicit regularization in deep matrix factorization. Adv. Neural Inf. Process. Syst., 32, 2019"},{"key":"361_CR37","unstructured":"Hern\u00e1ndez-Garc\u00eda, A., K\u00f6nig, P.: Data augmentation instead of explicit regularization. CoRR, abs\/1806.03852, (2018)"},{"key":"361_CR38","unstructured":"Barrett, D.\u00a0G.\u00a0T., Dherin, B.: Implicit gradient regularization. In:9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, (2021)"},{"key":"361_CR39","unstructured":"NIST Information Technology Laboratory. Nist lightweight cryptography standardization process. The National Institute of Standards and Technology, 2023. https:\/\/csrc.nist.gov\/News\/2023\/lightweight-cryptography-nist-selects-ascon"},{"key":"361_CR40","doi-asserted-by":"crossref","unstructured":"Bertoni, G., Daemen, J., Peeters, M., Van\u00a0Assche, G.: Duplexing the sponge: single-pass authenticated encryption and other applications. In: Selected Areas in Cryptography: 18th International Workshop, SAC 2011, Toronto, ON, Canada, August 11-12, 2011, Revised Selected Papers 18, pp. 320\u2013337. Springer, (2012)","DOI":"10.1007\/978-3-642-28496-0_19"},{"key":"361_CR41","unstructured":"Dobraunig, C., Eichlseder, M., Mendel, F., Schl\u00e4ffer, M.: Ascon v1. 2. Submission to the CAESAR Competition, 5(6):7, (2016)"}],"container-title":["Journal of Cryptographic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13389-024-00361-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13389-024-00361-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13389-024-00361-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T14:13:55Z","timestamp":1729001635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13389-024-00361-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,7]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["361"],"URL":"https:\/\/doi.org\/10.1007\/s13389-024-00361-5","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2386625\/v1","asserted-by":"object"}]},"ISSN":["2190-8508","2190-8516"],"issn-type":[{"value":"2190-8508","type":"print"},{"value":"2190-8516","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,7]]},"assertion":[{"value":"16 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}