Machine Learning and Applied Cryptography
1La Trobe University, Melbourne, Australia
2Qatar University, Doha, Qatar
3Georgia Gwinnett College, Lawrenceville, USA
4HITEC University, Taxila, Pakistan
5King Khalid University, Abha, Saudi Arabia
Machine Learning and Applied Cryptography
Description
Machine Learning (ML) and cryptography have many things in common; the amount of data to be handled and large search spaces for instance. The application of ML in cryptography is not new, but with over 3 quintillion bytes of data being generated every day, it is now more relevant to apply ML techniques in cryptography than ever before.
ML generally automates analytical model building to continuously learn and adapt to the large amount of data being fed as input. ML techniques can be used to indicate the relationship between the input and output data created by cryptosystems. ML techniques such as Boosting and Mutual Learning can be used to create the private cryptographic key over the public and insecure channel. Methods such as Naive Bayesian, support vector machine, and AdaBoost, which come under the category of classification, can be used to classify the encrypted traffic and objects into steganograms used in steganography. Besides the application in cryptography, which is an art of creating secure systems for encrypting/decrypting confidential data, the ML techniques can also be applied in cryptanalysis, which is an art of breaking cryptosystems to perform certain side-channel attacks.
The aim of this Special Issue is to create a volume of recent works on advances in all aspects of ML applications in cryptosystems and cryptanalysis. Both original research articles, and review articles discussing the current state of the art, are welcomed.
Potential topics include but are not limited to the following:
- Machine learning to analyze cryptosystems
- Machine learning to perform cryptanalysis
- Machine learning based intrusion detection
- Deep learning for security and privacy
- Data mining for authentication
- End-to-end system security models
- Machine learning based key exchange framework
- Machine learning based threat and attack model generation
- Nonlinear aspects of cryptosystems
- Adversarial machine learning for data security