Indonesian Journal of Electrical Engineering and Computer Science Vol. 38, No. 2, May 2025, pp. 1115~1123 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v38.i2.pp1115-1123  1115 Journal homepage: http://ijeecs.iaescore.com Deep learning-based cryptanalysis in recovering the secret key and plaintext on lightweight cryptography Yulia Fatma 1,2 , Muhammad Akmal Remli 2,3 , Mohd Saberi Mohamad 4 , Januar Al Amien 1,2 1 Department of Informatics Engineering, Faculty of Computer Science, Universitas Muhammadiyah Riau, Riau, Indonesia 2 Faculty of Data Science and Computing, Universiti Malaysia Kelantan, Kelantan, Malaysia 3 Institute for Artificial Intelligence and Big Data, Universiti Malaysia Kelantan, Kelantan, Malaysia 4 Health Data Science Lab, Department of Genetics and Genomics, College of Medicine and Health Sciences, United Arab Emirates University, Abu Dhabi, United Arab Emirates Article Info ABSTRACT Article history: Received May 22, 2024 Revised Nov 6, 2024 Accepted Nov 11, 2024 The development of machine learning (ML) technologies provide a new development direction for cryptanalysis. Several ML research in the field of cryptanalysis was carried out to identify the cryptographic algorithm used, find out the secret key, and even recover the secret message The first objective of this study is to see how much influence optimization and activation function have on the multi-layer perceptron (MLP) model in performing cryptanalysis. The second research objective, which is to compare the performance of cryptanalysis in recovering keys and the plaintext. Several experiments have been carried out, the observed parameters found that the use of the rectified linear unit (ReLU) activation function and the ADAM optimizer improves the performance of deep learning (DL)-based cryptanalysis as evidenced by a significantly smaller error rate. DL-based cryptanalysis works more effectively in recovering keys than recovering plaintext. DL-based cryptanalysis managed to recover the keys with an average loss of 0.007, an average of 49 epochs, and an average time of 0.178 minutes. Keywords: ADAM Cryptanalysis Deep learning Multi-layer perceptron S-DES This is an open access article under the CC BY-SA license. Corresponding Author: Muhammad Akmal Remli Faculty of Data Science and Computing, Universiti Malaysia Kelantan Kelantan, Malaysia Email: akmal@umk.edu.my 1. INTRODUCTION Cryptography is the study of techniques to ascertain confidentiality and or authenticity of information. Cryptography research primarily focuses on two areas: cryptographic design and cryptanalysis [1]. Cryptanalysis, commonly known as “code-breaking,” involves techniques to decipher encrypted information. Cryptanalysis is the techniques used for deciphering a message without any knowledge of the enciphering [2]. Existing cryptanalytic techniques no longer work on new algorithms [3]. Traditional cryptanalysis techniques tend to require a large amount of time and resources so that they are not compatible with new algorithms, so a new cryptanalysis technique is needed [4]. Advancements in machine learning (ML) technology offer a new direction for cryptography and cryptanalysis [5]. The connection between cryptography and ML was initially introduced in 1991 [6]. Since then, numerous researchers have explored using ML techniques to conduct cryptanalysis on block ciphers. Several ML research in the field of cryptanalysis was carried out to guess or identify the cryptographic algorithm used, guess the S-Box, find out the secret key and even recover the secret message [4], [7], [8]. Based on previous studies, AI capabilities,