DeCrypt: a 3DES inspired optimised cryptographic algorithm

Cybersecurity has become one of the focuses of organisations. The number of cyberattacks keeps increasing as Internet usage continues to grow. As new types of cyberattacks continue to emerge, researchers focus on developing machine learning (ML)-based intrusion detection systems (IDS) to detect zero-day attacks. They usually remove some or all attack samples from the training dataset and only include them in the testing dataset when evaluating the performance. This method may detect unknown attacks; however, it does not reflect the long-term performance of the IDS as it only shows the changes in the type of attacks. In this work, we focused on evaluating the long-term performance of ML-based IDS. To achieve this goal, we proposed evaluating the ML-based IDS using a dataset created later than the training dataset. The proposed method can better assess the long-term performance as the testing dataset reflects the changes in the attack type and network infrastructure changes over time. We have implemented six of the most popular ML models, including decision tree (DT), random forest (RF), support vector machine (SVM), naïve Bayes (NB), artificial neural network (ANN), and deep neural network (DNN). These models are trained and tested with a pair of datasets with symmetrical classes. Our experiments using the CIC-IDS2017 and the CSE-CIC-IDS2018 datasets show that SVM and ANN are most resistant to overfitting. Our experiments also indicate that DT and RF suffer the most from overfitting, although they perform well on the training dataset. On the other hand, our experiments using the LUFlow dataset have shown that all models can perform well when the difference between the training and testing datasets is small.

/pdf/evaluation-of-machine-learning-algorithms-in-network-based-3htz2iic.pdf

Evaluation of Machine Learning Algorithms in Network-Based Intrusion Detection Using Progressive Dataset

Industrial information security is an important part of the national security strategy that affects the economy and people’s lives. With the rapid development of automation and information technology, common protocols and common hardware and software based on information technology are increasingly used in industrial information control system products and are widely used in industries such as energy, metallurgy, water resource management, chemical, and production. Attacks on critical industrial information can not only cause accidents, losses, and local production pollution but also disrupt the balance of supply and demand of raw materials in the area covered by the system. Therefore, it is of great theoretical and practical importance to study industrial information security as an important measure to ensure the stable operation of the system. In this paper, we analyze the main industrial structure characteristics, external environment, and security requirements and propose a monitoring and warning platform architecture with cryptographic antitheft technology system based on hierarchical modeling and closed-loop control. It can prevent the spread of the attack and reduce its negative impact.

Industrial Information Security Detection and Protection: Monitoring and Warning Platform Architecture Design and Cryptographic Antitheft Technology System Upgrade

Due to the rapid growth of cyber-security challenges via sophisticated attacks such as data injection attacks, replay attacks, etc., cyber-attack detection and avoidance system has become a significant area of research in Cyber-Physical Systems (CPSs). It is possible for different attacks to cause system failures, malfunctions. In the future, CPSs may require a cyber-defense system for improving its security. The different deep learning algorithms based on cyber-attack detection techniques have been considered for the detection and mitigation of different types of cyber-attacks. In this paper, the newly suggested deep learning algorithms for cyber-attack detection are studied and a hybrid deep learning model is proposed. The proposed Hybrid Convolutional Multilayer Perceptron for Cyber Physical Systems (HCMP-CPS) model is based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP). The HCMP-CPS model helps to detect and classify attacks more accurately than the conventional models. 

Hybrid Convolutional Multilayer Perceptron for Cyber Physical Systems (HCMP-CPS)

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.

Bang Yuan Chong

Papers

Investigating Deep Learning Approaches on the Security Analysis of Cryptographic Algorithms