Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms
Bang Yuan Chong,Iftekhar Salam +1 more
- Vol. 5, Iss: 4, pp 30
Reads0
Chats0
TLDR
In this paper, the authors investigated the use of deep learning (DL) models under a known-plaintext scenario to predict the secret key of a cipher using DL techniques and showed that DL models can successfully recover the random key of Simplified Data Encryption Standard (S-DES), Speck, Simeck and Katan.Abstract:
This paper studies the use of deep learning (DL) models under a known-plaintext scenario. The goal of the models is to predict the secret key of a cipher using DL techniques. We investigate the DL techniques against different ciphers, namely, Simplified Data Encryption Standard (S-DES), Speck, Simeck and Katan. For S-DES, we examine the classification of the full key set, and the results are better than a random guess. However, we found that it is difficult to apply the same classification model beyond 2-round Speck. We also demonstrate that DL models trained under a known-plaintext scenario can successfully recover the random key of S-DES. However, the same method has been less successful when applied to modern ciphers Speck, Simeck, and Katan. The ciphers Simeck and Katan are further investigated using the DL models but with a text-based key. This application found the linear approximations between the plaintext–ciphertext pairs and the text-based key.read more
Citations
More filters
Journal ArticleDOI
DeCrypt: a 3DES inspired optimised cryptographic algorithm
Deepraj Chowdhury,Ajoy Dey,Ritam Garai,Subhrangshu Adhikary,Ashutosh Dhar Dwivedi,Uttam Ghosh,Waleed S. Alnumay +6 more
Journal ArticleDOI
Evaluation of Machine Learning Algorithms in Network-Based Intrusion Detection Using Progressive Dataset
T. Chua,Iftekhar Salam +1 more
TL;DR: In this article, the authors evaluated the long-term performance of ML-based IDS using a dataset created later than the training dataset, which can better assess the longterm performance as the testing dataset reflects the changes in the attack type and network infrastructure changes over time.
Journal ArticleDOI
Industrial Information Security Detection and Protection: Monitoring and Warning Platform Architecture Design and Cryptographic Antitheft Technology System Upgrade
TL;DR: This paper analyzes the main industrial structure characteristics, external environment, and security requirements and proposes a monitoring and warning platform architecture with cryptographic antitheft technology system based on hierarchical modeling and closed-loop control.
Book ChapterDOI
Hybrid Convolutional Multilayer Perceptron for Cyber Physical Systems (HCMP-CPS)
TL;DR: In this paper , the authors proposed a hybrid deep learning model for cyber-attack detection and avoidance in Cyber-Physical Systems (CPSs) based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), and Hybrid convolutional multilayer perceptron for Cyber Physical Systems (HCMP-CPS) model.
References
More filters
Book ChapterDOI
KATAN and KTANTAN -- A Family of Small and Efficient Hardware-Oriented Block Ciphers
TL;DR: A new family of very efficient hardware oriented block ciphers divided into two flavors, which is more compact in hardware, as the key is burnt into the device (and cannot be changed), and achieves encryption speed of 12.5 KBit/sec.
Proceedings ArticleDOI
The SIMON and SPECK lightweight block ciphers
TL;DR: Simplicity, security, and flexibility are ever-present yet conflicting goals in cryptographic design and these goals were balanced in the design of Simon and Speck.
Journal ArticleDOI
Machine learning in side-channel analysis: a first study
TL;DR: This work comprehensively investigates the application of a machine learning technique in SCA, a powerful kernel-based learning algorithm: the Least Squares Support Vector Machine (LS-SVM) and the target is a software implementation of the Advanced Encryption Standard.
Book ChapterDOI
The Simeck Family of Lightweight Block Ciphers
TL;DR: Simeck as discussed by the authors combines the good design components from both Simon and Speck, in order to devise even more compact and efficient block ciphers, which can satisfy the area, power, and throughput requirements in passive RFID tags.
Book ChapterDOI
Differential Cryptanalysis of Round-Reduced Simon and Speck
TL;DR: This paper presents differential attacks on Simon and Speck, two families of lightweight block ciphers that were presented by the U.S. National Security Agency in June 2013 and demonstrates the drawback of the intensive optimizations in Simon andspeck.