{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:15:31Z","timestamp":1777043731517,"version":"3.51.4"},"reference-count":40,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"PQC project of JCASC (School of Integrated Circuits of Tsinghua University \u2013 Tongxin Microelectronics Co. Ltd. Joint Research Center for Automotive and Security Chip)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cryptography"],"abstract":"<jats:p>Deep learning-based side-channel analysis is one of the most effective techniques for extracting and classifying sensitive information from a target device. This paper demonstrates the best-performing deep learning model for the target implementation by evaluating various deep learning architectures, including MLP, CNN, and RNN, while systematically optimizing their hyperparameters to achieve the best performance. The paper uses a case study of the Number Theoretic Transform accelerator for the CRYSTALS-Kyber key encapsulation mechanism to show that enhanced deep learning analysis can be used to break security. The best-performing deep learning-based model achieved a 96.64% accuracy in classifying pairwise coefficients of the s vector, which is used to generate the secret key with the NTT accelerator for Kyber768 and Kyber1024. For Kyber512, the model achieved an accuracy of 95.71%. The proposed approach significantly improves average training efficiency, with POIs achieving up to 1.45 times faster performance for MLP models, 10.53 times faster for CNNs, and 10.28 times faster for RNNs compared to deep learning methods without POIs, while maintaining high accuracy in side-channel analysis.<\/jats:p>","DOI":"10.3390\/cryptography9040064","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T09:41:02Z","timestamp":1760002862000},"page":"64","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Comparative Deep Learning-Based Side-Channel Analysis of an FPGA-Based CRYSTALS-Kyber NTT Accelerator"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4101-7269","authenticated-orcid":false,"given":"Munkhbaatar","family":"Chinbat","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology, Beijing 100084, China"}]},{"given":"Liji","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology, Beijing 100084, China"}]},{"given":"Xiangmin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology, Beijing 100084, China"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Tsinghua University, Beijing 100084, China"},{"name":"Beijing National Research Center for Information Science and Technology, Beijing 100084, China"}]},{"given":"Man","family":"Wei","sequence":"additional","affiliation":[{"name":"Tongxin Microelectronics Co., Ltd., Beijing 100192, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mayer-Sommer, R. (2000, January 17\u201318). Smartly analyzing the simplicity and the power of simple power analysis on smartcards. Proceedings of the International Workshop on Cryptographic Hardware and Embedded Systems, Worcester, MA, USA.","DOI":"10.1007\/3-540-44499-8_6"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kocher, P. (1999, January 15\u201319). Differential power analysis. Proceedings of the Advances in Cryptology (CRYPTO\u201999), Santa Barbara, CA, USA.","DOI":"10.1007\/3-540-48405-1_25"},{"key":"ref_3","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-CHES 2002: 4th International Workshop, Redwood Shores, CA, USA. Revised Papers 4.","DOI":"10.1007\/3-540-36400-5_3"},{"key":"ref_4","unstructured":"Schramm, K., Leander, G., Felke, P., and Paar, C. (2004, January 11\u201313). A collision-attack on AES: Combining side channel-and differential-attack. Proceedings of the Cryptographic Hardware and Embedded Systems-CHES 2004: 6th International Workshop, Cambridge, MA, USA. Proceedings 6."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","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_6","first-page":"1","article-title":"Study of Deep Learning Techniques for Side-Channel Analysis and Introduction to ASCAD Database","volume":"53","author":"Prouff","year":"2018","journal-title":"CoRR"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cagli, E., Dumas, C., and Prouff, E. (2017, January 25\u201328). Convolutional neural networks with data augmentation against jitter-based countermeasures: Profiling attacks without pre-processing. Proceedings of the Cryptographic Hardware and Embedded Systems\u2013CHES 2017: 19th International Conference, Taipei, Taiwan.","DOI":"10.1007\/978-3-319-66787-4_3"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bazangani, O., Eliasi, P.A., Picek, S., and Batina, L. (2024, January 25\u201327). Can Machine Learn Pipeline Leakage?. Proceedings of the 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), Valencia, Spain.","DOI":"10.23919\/DATE58400.2024.10546629"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1109\/TETC.2022.3218372","article-title":"I Choose You: Automated Hyperparameter Tuning for Deep Learning-based Side-channel Analysis","volume":"12","author":"Wu","year":"2022","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/TCAD.2024.3518414","article-title":"Less Traces Are All It Takes: Efficient Side-Channel Analysis on AES","volume":"44","author":"Xiao","year":"2024","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Durvaux, F., and Standaert, F.X. (2016, January 8\u201312). From improved leakage detection to the detection of points of interests in leakage traces. Proceedings of the Advances in Cryptology\u2013EUROCRYPT 2016: 35th Annual International Conference on the Theory and Applications of Cryptographic Techniques, Vienna, Austria. Part I 35.","DOI":"10.1007\/978-3-662-49890-3_10"},{"key":"ref_12","unstructured":"Becker, G., Cooper, J., DeMulder, E., Goodwill, G., Jaffe, J., Kenworthy, G., Kouzminov, T., Leiserson, A., Marson, M., and Rohatgi, P. (2013, January 24\u201326). Test vector leakage assessment (TVLA) methodology in practice. Proceedings of the International Cryptographic Module Conference, Gaithersburg, MD, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"105112","DOI":"10.1016\/j.ic.2023.105112","article-title":"Roadmap of post-quantum cryptography standardization: Side-channel attacks and countermeasures","volume":"295","author":"Shaller","year":"2023","journal-title":"Inf. Comput."},{"key":"ref_14","unstructured":"National Institute of Standards and Technology (2024, December 15). Module-Lattice-Based Key-Encapsulation Mechanism Standard, Available online: https:\/\/nvlpubs.nist.gov\/nistpubs\/FIPS\/NIST.FIPS.203.pdf."},{"key":"ref_15","unstructured":"Maghrebi, H. (2024, December 20). Deep Learning Based Side Channel Attacks in Practice. Cryptology ePrint Archive. Available online: https:\/\/eprint.iacr.org\/2019\/578."},{"key":"ref_16","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_17","doi-asserted-by":"crossref","first-page":"422","DOI":"10.46586\/tches.v2023.i3.422-444","article-title":"Deep Learning Side-Channel Collision Attack","volume":"2023","author":"Staib","year":"2023","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"828","DOI":"10.46586\/tches.v2022.i4.828-861","article-title":"Exploring Feature Selection Scenarios for Deep Learning-based Side-channel Analysis","volume":"2022","author":"Perin","year":"2022","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1007\/s13389-023-00320-6","article-title":"No (good) loss no gain: Systematic evaluation of loss functions in deep learning-based side-channel analysis","volume":"13","author":"Kerkhof","year":"2023","journal-title":"J. Cryptogr. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"24","DOI":"10.46586\/tches.v2023.i2.24-53","article-title":"Peek into the Black-Box: Interpretable Neural Network using SAT Equations in Side-Channel Analysis","volume":"2023","author":"Yap","year":"2023","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3906","DOI":"10.1109\/TIFS.2022.3176189","article-title":"Towards Human Dependency Elimination: AI Approach to SCA Robustness Assessment","volume":"17","author":"Rioja","year":"2022","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1109\/TC.2023.3299045","article-title":"Multivariate TVLA\u2014Efficient Side-Channel Evaluation using Confidence Intervals","volume":"74","author":"Bache","year":"2023","journal-title":"IEEE Trans. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105326","DOI":"10.1109\/ACCESS.2024.3416199","article-title":"A Novel Side-Channel Archive Framework Using Deep Learning-Based Leakage Compression","volume":"12","author":"Jung","year":"2024","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Gupta, P., Ramaswamy, A., Drees, J.P., H\u00fcllermeier, E., Priesterjahn, C., and Jager, T. (2022, January 3\u20135). Automated Information Leakage Detection: A New Method Combining Machine Learning and Hypothesis Testing with an Application to Side-channel Detection in Cryptographic Protocols. Proceedings of the 14th International Conference on Agents and Artificial Intelligence. Science and Technology Publications, Virtual.","DOI":"10.5220\/0010793000003116"},{"key":"ref_25","unstructured":"Saha, S., Alam, M., Bag, A., Mukhopadhyay, D., and Dasgupta, P. (2024, December 20). Leakage Assessment in Fault Attacks: A Deep Learning Perspective. Cryptology ePrint Archive. Available online: https:\/\/eprint.iacr.org\/2020\/306."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"552","DOI":"10.46586\/tches.v2021.i3.552-598","article-title":"DL-LA: Deep Learning Leakage Assessment: A Modern Roadmap for SCA Evaluations","volume":"2021","author":"Moos","year":"2021","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2340","DOI":"10.1109\/TIFS.2024.3350375","article-title":"Deep Learning Gradient Visualization-Based Pre-Silicon Side-Channel Leakage Location","volume":"19","author":"Li","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yaman, F., Mert, A.C., \u00d6zt\u00fcrk, E., and Sava\u015f, E. (2021, January 1\u20135). A hardware accelerator for polynomial multiplication operation of CRYSTALS-KYBER PQC scheme. Proceedings of the 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France.","DOI":"10.23919\/DATE51398.2021.9474139"},{"key":"ref_29","first-page":"513","article-title":"Applying TVLA to Public Key Cryptographic Algorithms","volume":"2016","author":"Tunstall","year":"2016","journal-title":"IACR Cryptol. ePrint Arch."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, Y., and Tang, M. (2023). A Survey of Side-Channel Leakage Assessment. Electronics, 12.","DOI":"10.3390\/electronics12163461"},{"key":"ref_31","first-page":"1","article-title":"CRYSTALS-Kyber algorithm specifications and supporting documentation","volume":"2","author":"Avanzi","year":"2019","journal-title":"NIST PQC Round"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bisheh-Niasar, M., Azarderakhsh, R., and Mozaffari-Kermani, M. (2021, January 14\u201316). High-speed NTT-based polynomial multiplication accelerator for post-quantum cryptography. Proceedings of the 2021 IEEE 28th Symposium on Computer Arithmetic (ARITH), Lyngby, Denmark.","DOI":"10.1109\/ARITH51176.2021.00028"},{"key":"ref_33","unstructured":"Inc., N.T (2024, January 15). ChipWhisperer: An Open-Source Side-Channel Analysis Toolchain. Available online: https:\/\/github.com\/newaetech\/chipwhisperer."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chinbat, M., Wu, L., Zhang, X., Batsukh, A., Yang, Y., and Wu, L. (2023, January 1\u20133). Evaluating Side-Channel Attack Vulnerabilities in Post-Quantum CRYSTALS-Kyber Hardware Based on Simple Power Analysis. Proceedings of the 2023 IEEE 17th International Conference on Anti-Counterfeiting, Security, and Identification (ASID), Xiamen, China.","DOI":"10.1109\/ASID60355.2023.10426450"},{"key":"ref_35","first-page":"140","article-title":"The pareto principle","volume":"7","author":"Dunford","year":"2014","journal-title":"Plymouth Stud. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"3353","DOI":"10.1109\/TIFS.2024.3359890","article-title":"Zero-Value Filtering for Accelerating Non-Profiled Side-Channel Attack on Incomplete NTT based Implementations of Lattice-based Cryptography","volume":"19","author":"Tosun","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ravi, P., Jap, D., Bhasin, S., and Chattopadhyay, A. (November, January 28). Machine Learning Based Blind Side-Channel Attacks on PQC-Based KEMs-A Case Study of Kyber KEM. Proceedings of the 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD), San Francisco, CA, USA.","DOI":"10.1109\/ICCAD57390.2023.10323721"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ji, Y., Wang, R., Ngo, K., Dubrova, E., and Backlund, L. (2023, January 22\u201326). A side-channel attack on a hardware implementation of CRYSTALS-Kyber. Proceedings of the 2023 IEEE European Test Symposium (ETS), Venezia, Italy.","DOI":"10.1109\/ETS56758.2023.10174000"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ji, Y., and Dubrova, E. (2023, January 30). A Side-Channel Attack on a Masked Hardware Implementation of CRYSTALS-Kyber. Proceedings of the 2023 Workshop on Attacks and Solutions in Hardware Security, Copenhagen, Denmark.","DOI":"10.1145\/3605769.3623992"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.1109\/TC.2021.3122997","article-title":"Magnifying side-channel leakage of lattice-based cryptosystems with chosen ciphertexts: The case study of kyber","volume":"71","author":"Xu","year":"2021","journal-title":"IEEE Trans. Comput."}],"container-title":["Cryptography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2410-387X\/9\/4\/64\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:50:50Z","timestamp":1760035850000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2410-387X\/9\/4\/64"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":40,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["cryptography9040064"],"URL":"https:\/\/doi.org\/10.3390\/cryptography9040064","relation":{},"ISSN":["2410-387X"],"issn-type":[{"value":"2410-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]}}}