Recent advances in machine learning have opened new directions in the cryptanalysis of lightweight block ciphers, particularly in the study of nonlinear components and key-dependent transformations. Building on prior work involving simplified cryptographic models such as Mini-AES and deep-learning-based attacks on lightweight ciphers, this study investigates the learnability of round-key bits in the Simplified Advanced Encryption Standard (S-AES). A structured dataset was generated by producing random 16-bit master keys and deriving their corresponding 48-bit subkey representations through the key-schedule algorithm. Additionally, two fixed plaintext blocks were encrypted under each key to construct three distinct training sets for the classification of the KPK_PKP, KFK_FKF, and KSK_SKS round-key bits. To examine the predictive potential of machine-learning models, Support Vector Machines (SVMs) were chosen as primary classifiers due to their robustness and proven ability to capture nonlinear decision boundaries even in limited training regimes. The Ray Tune optimization framework was employed to identify optimal SVM hyperparameters, leveraging distributed search mechanisms that have demonstrated superior performance compared with conventional optimizers such as HyperOpt and SMAC. Experimental evaluations conducted on datasets consisting of 1500 samples - split into 1200 training and 300 testing instances - reveal that certain round-key bits exhibit significantly higher learnability than others, indicating non-uniform structural leakage within the S-AES key schedule. The results highlight that optimized SVM configurations can achieve strong classification performance across multiple round-key bit positions, demonstrating the presence of machine-learnable relationships between plaintext–ciphertext mappings and internal subkey bits. These findings contribute to a deeper understanding of cryptanalytic vulnerabilities in lightweight block ciphers and confirm the growing relevance of machine-learning-driven approaches in modern symmetric cryptography research.

S-AES, lightweight cryptography, key-bit classification

W. Zhang, E. Pasalic, “Highly nonlinear balanced S-boxes with good differential properties,” IEEE Transactions on Information Theory, vol. 60, no. 12, pp. 7970–7979, 2014.

Yong Wang, Zhiqiang Zhang, Leo Yu Zhang, Jun Feng, Jerry Gao, Peng Lei, “A genetic algorithm for constructing bijective substitution boxes with high nonlinearity,” Information Sciences, vol. 523, pp. 152–166, 2020.

H. Zahid et al., “Efficient Dynamic S-Box Generation Using Linear Trigonometric Transformation for Security Applications,” IEEE Access, vol. 9, pp. 98460–98475, 2021.

M. Ahmad and M. Malik, “Design of chaotic neural network based method for cryptographic substitution box,” ICEEOT 2016, Chennai, India, pp. 864–868.

R. C. Phan, “Mini Advanced Encryption Standard (Mini-AES): A Testbed for Cryptanalysis Students,” Cryptologia, vol. 26, no. 4, pp. 283–306, 2002.

Kuryazov D.M, Sattarov A.B, Axmedov B.B, Blokli simmetrik shifrlash algoritmlari bardoshliligini zamonaviy kriptotahlil usullari bilan baholash, Tashkent, 2017.

B. F. Abduraximov, J. R. Abdurazzoqov, “Deep learning-based cryptanalysis of Simplified AES,” Informatika va Energetika Muammolari, vol. 2, pp. 17–26, 2023.

A. Bakhtiyor, B. Ilkhom, A. Javokhir, A. Orif, “Using the Capabilities of Artificial Neural Networks in the Cryptanalysis of Symmetric Lightweight Block Ciphers,” 2024, pp. 113–121.

B. Y. Sun, D.-S. Huang, H.-T. Fang, “Lidar signal denoising using least-squares support vector machine,” IEEE Signal Processing Letters, vol. 12, pp. 101–104, 2005.

A. Kazemi, R. Boostani, M. Odeh, M. R. Al-Mousa, “Two-Layer SVM: Towards Deep Statistical Learning,” EICEEAI 2022, IEEE, 2022.

P. Chen, B. Wang, H.-S. Wong, D.-S. Huang, “Prediction of protein B-factors using multi-class bounded SVM,” Protein and Peptide Letters, vol. 14, no. 2, pp. 185–190, 2007.

N. Cristianini, J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, 2000.

C. J. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121–167, 1998.

Hyperopt Documentation. Retrieved: 11 March 2024. https://hyperopt.github.io/hyperopt/

M. Lindauer et al., “SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization,” JMLR, vol. 23, no. 54, pp. 1–9, 2022.

S. Shekhar, A. Bansode, A. Salim, “A Comparative Study of Hyper-Parameter Optimization Tools,” IEEE CSDE 2021, pp. 1–6.

J. Parra-Ullauri, X. Zhang, A. Bravalheri, R. Nejabati, D. Simeonidou, “Federated Hyperparameter Optimisation with Flower and Optuna,” ACM SAC 2023, pp. 1209–1216.

Y. Bengio, “Practical Recommendations for Gradient-Based Training of Deep Architectures,” 2012, pp. 437–478.

Y. Bengio, “Gradient-Based Optimization of Hyperparameters,” Neural Computation, vol. 12, no. 8, pp. 1889–1900, 2000.

K. R. Khamdamovich, H. Elshod, “Detecting spam messages using naive Bayes,” ICISCT 2021, IEEE, pp. 1–3.

J. Snoek, H. Larochelle, R. Adams, “Practical Bayesian Optimization of Machine Learning Algorithms,” NIPS, 2012.

L. Li, K. G. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar, “Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization,” JMLR, vol. 18, 2016.

Real E. et al., “Large-Scale Evolution of Image Classifiers,” ICML 2017.

Bekmuratov T.F., Mukhamedieva D.T., Bobomurodov O.J., “Models of fuzzy criteria and algorithms for weakly structured decisions,” Mashinastrenie i Kompyuternie Texnologii, vol. 7, 2010.

A. D. Dwivedi, G. Srivastava, “Security analysis of lightweight IoT encryption algorithms: SIMON and SIMECK,” Internet of Things, vol. 21, p. 100677, 2023.

J. So, “Deep Learning-Based Cryptanalysis of Lightweight Block Ciphers,” Security and Communication Networks, 2020.

[A. Jain, V. Kohli, G. Mishra, “Deep Learning-Based Differential Distinguisher for PRESENT,” IACR ePrint, 2020/846.

H. Kim, S. Lim, Y. Kang, W. Kim, D. Kim, S. Yoon, H. Seo, “Deep-Learning-Based Cryptanalysis of Lightweight Block Ciphers Revisited,” Entropy, vol. 25, no. 7, p. 986, 2023.

H. Grari et al., “Deep Learning-Based Cryptanalysis of a Simplified AES Cipher,” International Journal of Information Security and Privacy, vol. 16, no. 1, pp. 1–16, 2022.

H. Kimura et al., “Output Prediction Attacks on Block Ciphers Using Deep Learning,” 2022.

Abdurazzoqov J. R., Nochiziqli komponentlarni shakllantirish va tasniflash algoritmlari, PhD Dissertation, Tashkent, 2024.