{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:55:16Z","timestamp":1760147716812,"version":"build-2065373602"},"reference-count":33,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:00:00Z","timestamp":1677110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The adoption of deep neural networks for profiling side-channel attacks opened new perspectives for leakage detection. Recent publications showed that cryptographic implementations featuring different countermeasures could be broken without feature selection or trace preprocessing. This success comes with a high price: an extensive hyperparameter search to find optimal deep learning models. As deep learning models usually suffer from overfitting due to their high fitting capacity, it is crucial to avoid over-training regimes, which require a correct number of epochs. For that, early stopping is employed as an efficient regularization method that requires a consistent validation metric. Although guessing entropy is a highly informative metric for profiling side-channel attacks, it is time-consuming, especially if computed for all epochs during training, and the number of validation traces is significantly large. This paper shows that guessing entropy can be efficiently computed during training by reducing the number of validation traces without affecting the efficiency of early stopping decisions. Our solution significantly speeds up the process, impacting the performance of the hyperparameter search and overall profiling attack. Our fast guessing entropy calculation is up to 16\u00d7 faster, resulting in more hyperparameter tuning experiments and allowing security evaluators to find more efficient deep learning models.<\/jats:p>","DOI":"10.3390\/a16030127","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T01:37:52Z","timestamp":1677202672000},"page":"127","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["The Need for Speed: A Fast Guessing Entropy Calculation for Deep Learning-Based SCA"],"prefix":"10.3390","volume":"16","author":[{"given":"Guilherme","family":"Perin","sequence":"first","affiliation":[{"name":"Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lichao","family":"Wu","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering, Mathematics & Computer Science, Delft University of Technology, Mekelweg 5, 2628 CD Delft, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7509-4337","authenticated-orcid":false,"given":"Stjepan","family":"Picek","sequence":"additional","affiliation":[{"name":"Digital Security Group, Radboud University, Houtlaan 4, 6525 XZ Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chari, S., Rao, J.R., and Rohatgi, P. (2002, January 13\u201315). Template Attacks. Proceedings of the Cryptographic Hardware and Embedded Systems\u2014CHES 2002, Redwood Shores, CA, USA.","DOI":"10.1007\/3-540-36400-5_3"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/11545262_3","article-title":"A Stochastic Model for Differential Side Channel Cryptanalysis","volume":"Volume 3659","author":"Rao","year":"2005","journal-title":"Proceedings of the Cryptographic Hardware and Embedded Systems\u2014CHES 2005, 7th International Workshop"},{"key":"ref_3","first-page":"388","article-title":"Differential Power Analysis","volume":"Volume 1666","author":"Wiener","year":"1999","journal-title":"Proceedings of the Advances in Cryptology\u2014CRYPTO \u201999, 19th Annual International Cryptology Conference"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/978-3-540-28632-5_2","article-title":"Correlation Power Analysis with a Leakage Model","volume":"Volume 3156","author":"Joye","year":"2004","journal-title":"Proceedings of the Cryptographic Hardware and Embedded Systems\u2014CHES 2004: 6th International Workshop"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1007\/978-3-540-85053-3_27","article-title":"Mutual Information Analysis","volume":"Volume 5154","author":"Oswald","year":"2008","journal-title":"Proceedings of the Cryptographic Hardware and Embedded Systems\u2014CHES 2008, 10th International Workshop"},{"key":"ref_6","unstructured":"Nebel, W., and Atienza, D. (2015, January 9\u201313). Reliable information extraction for single trace attacks. Proceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition, DATE 2015, Grenoble, France."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/s13389-014-0089-3","article-title":"A machine learning approach against a masked AES\u2014Reaching the limit of side-channel attacks with a learning model","volume":"5","author":"Lerman","year":"2015","journal-title":"J. Cryptogr. Eng."},{"key":"ref_8","first-page":"1","article-title":"Methodology for Efficient CNN Architectures in Profiling Attacks","volume":"2020","author":"Zaid","year":"2020","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"677","DOI":"10.46586\/tches.v2021.i3.677-707","article-title":"Reinforcement Learning for Hyperparameter Tuning in Deep Learning-based Side-channel Analysis","volume":"2021","author":"Rijsdijk","year":"2021","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/978-3-319-66787-4_3","article-title":"Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures\u2013Profiling Attacks Without Pre-processing","volume":"Volume 10529","author":"Fischer","year":"2017","journal-title":"Proceedings of the Cryptographic Hardware and Embedded Systems\u2014CHES 2017\u201419th International Conference"},{"key":"ref_11","first-page":"348","article-title":"A Comprehensive Study of Deep Learning for Side-Channel Analysis","volume":"2020","author":"Masure","year":"2020","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_12","first-page":"209","article-title":"The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations","volume":"2019","author":"Picek","year":"2019","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/978-3-319-21476-4_2","article-title":"Template Attacks vs. Machine Learning Revisited (and the Curse of Dimensionality in Side-Channel Analysis)","volume":"Volume 9064","author":"Lerman","year":"2015","journal-title":"Lecture Notes in Computer Science"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"235","DOI":"10.46586\/tches.v2021.i3.235-274","article-title":"Pay Attention to Raw Traces: A Deep Learning Architecture for End-to-End Profiling Attacks","volume":"2021","author":"Lu","year":"2021","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"73","DOI":"10.46586\/tches.v2020.i3.73-96","article-title":"A Novel Evaluation Metric for Deep Learning-Based Side Channel Analysis and Its Extended Application to Imbalanced Data","volume":"2020","author":"Zhang","year":"2020","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_16","first-page":"25","article-title":"Ranking Loss: Maximizing the Success Rate in Deep Learning Side-Channel Analysis","volume":"2021","author":"Zaid","year":"2021","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/978-3-642-01001-9_26","article-title":"A unified framework for the analysis of side-channel key recovery attacks","volume":"5479","author":"Standaert","year":"2009","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/s13389-019-00220-8","article-title":"Deep learning for side-channel analysis and introduction to ASCAD database","volume":"10","author":"Benadjila","year":"2020","journal-title":"J. Cryptogr. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Picek, S., Heuser, A., Perin, G., and Guilley, S. (2021, January 11\u201312). Profiled Side-Channel Analysis in the Efficient Attacker Framework. Proceedings of the Smart Card Research and Advanced Applications: 20th International Conference, CARDIS 2021, L\u00fcbeck, Germany. Revised Selected Papers.","DOI":"10.1007\/978-3-030-97348-3_3"},{"key":"ref_20","unstructured":"Bhasin, S., Chattopadhyay, A., Heuser, A., Jap, D., Picek, S., and Shrivastwa, R.R. (March, January 27). Mind the Portability: A Warriors Guide through Realistic Profiled Side-channel Analysis. Proceedings of the 27th NDSS, San Diego, CA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"147","DOI":"10.46586\/tches.v2020.i3.147-168","article-title":"Revisiting a Methodology for Efficient CNN Architectures in Profiling Attacks","volume":"2020","author":"Wouters","year":"2020","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wu, L., Perin, G., and Picek, S. (2022). I Choose You: Automated Hyperparameter Tuning for Deep Learning-based Side-channel Analysis. IEEE Trans. Emerg. Top. Comput., 1\u201312.","DOI":"10.1109\/TETC.2022.3218372"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"337","DOI":"10.46586\/tches.v2020.i4.337-364","article-title":"Strength in Numbers: Improving Generalization with Ensembles in Machine Learning-based Profiled Side-channel Analysis","volume":"2020","author":"Perin","year":"2020","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Stamp, M., Aaron Visaggio, C., Mercaldo, F., and Di Troia, F. (2022). Artificial Intelligence for Cybersecurity, Springer International Publishing.","DOI":"10.1007\/978-3-030-97087-1"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Perin, G., Buhan, I., and Picek, S. (2021). Learning When to Stop: A Mutual Information Approach to Prevent Overfitting in Profiled Side-Channel Analysis, Springer.","DOI":"10.1007\/978-3-030-89915-8_3"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Robissout, D., Zaid, G., Colombier, B., Bossuet, L., and Habrard, A. (2020). Online Performance Evaluation of Deep Learning Networks for Profiled Side-Channel Analysis, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-68773-1_10"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Paguada, S., Batina, L., Buhan, I., and Armendariz, I. (2023). Being Patient and Persistent: Optimizing an Early Stopping Strategy for Deep Learning in Profiled Attacks. IEEE Trans. Comput., 1\u201312.","DOI":"10.1109\/TC.2023.3234205"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1145\/3569577","article-title":"SoK: Deep Learning-Based Physical Side-Channel Analysis","volume":"55","author":"Picek","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_29","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"148","DOI":"10.46586\/tches.v2019.i3.148-179","article-title":"Make Some Noise. Unleashing the Power of Convolutional Neural Networks for Profiled Side-channel Analysis","volume":"2019","author":"Kim","year":"2019","journal-title":"Iacr Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_31","unstructured":"O\u2019Malley, T., Bursztein, E., Long, J., Chollet, F., Jin, H., and Invernizzi, L. (2023, January 26). KerasTuner. Available online: https:\/\/github.com\/keras-team\/keras-tuner."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TIFS.2022.3144871","article-title":"Efficient Profiled Side-Channel Analysis of Masked Implementations, Extended","volume":"17","author":"Bronchain","year":"2022","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/978-3-030-26948-7_25","article-title":"Leakage Certification Revisited: Bounding Model Errors in Side-Channel Security Evaluations","volume":"Volume 11692","author":"Boldyreva","year":"2019","journal-title":"Proceedings of the Advances in Cryptology\u2014CRYPTO 2019\u201439th Annual International Cryptology Conference"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/3\/127\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:40:53Z","timestamp":1760121653000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/3\/127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,23]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["a16030127"],"URL":"https:\/\/doi.org\/10.3390\/a16030127","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2023,2,23]]}}}