Zurab Kochladze - Academia.edu (original) (raw)

Uploads

Papers by Zurab Kochladze

EPiC series in computing, Jan 23, 2018

E-mail is one of the most widespread communication method in twenty first century. People daily g... more E-mail is one of the most widespread communication method in twenty first century. People daily get e-mails in their inboxes, including permanently increasing number of unwanted notifications (spam) too. The advanced e-mail service packs and antiviruses contain spam filtration software. Nevertheless, to classify e-mails as spam, fully depends on user, as information acceptable (or vital) for one consumer, may be a spam for another. Hence, it is crucial to have automatic spam filtration system for every individual user. The paper discuss the solution, a system that filters emails through consumers' parameters and gradually learns how to filter them accordingly. The system is based on multi-layer neural network, which uses logistic activation function, learns via tutor and counter-spread algorithm of mistakes (a.k.a. method of supervised learning, backward propagation of errors).

The work deals with the problems of creating the knowledge base using artificial conceptual intel... more The work deals with the problems of creating the knowledge base using artificial conceptual intelligence, offers the reasoning mechanisms on the basis of logics, founded on the base of alternative sets, and discusses the applications of the knowledge to solve the problems of pattern recognition.

The paper discusses the modified variant of Hill's algorithm that can be used in the modern b... more The paper discusses the modified variant of Hill's algorithm that can be used in the modern block ciphers. Keywords: Symmetrical block cipher, Hill's algorithm, The principle of confusion and diffusion.

EPiC Series in Computing

The application of e-mail is the most widespread communication method. The increased email number... more The application of e-mail is the most widespread communication method. The increased email number includes permanently increased amount of unwanted notifications (spam). The statistics claims that 80% of the traffic is spam that lags the internet traffic, consumes space on hard disc, and reduces the capacity of the network, not to mention time spent for email’s classification. The advanced E-mail service packs contain spam filtration program. Nevertheless, to classify the e-mails as spam fully depends on the consumers, as information acceptable (or vital) for one consumer, may be a spam for other. Hence, it is crucial to have automatic spam filtration system for every individual consumer.The paper discuss the solution, a learning system that filters emails through consumers’ parameters and gradually learn how to filter them accordingly. The system based on multi-layer neural network, which uses logistic activation function, learns via tutor and counter-spread algorithm of mistakes

This paper discusses the use of genetic algorithms to cryptanalysis. Namely, how to break up the ... more This paper discusses the use of genetic algorithms to cryptanalysis. Namely, how to break up the Vigenere cipher with the genetic algorithm and why it is impossible to break complete the cipher with this method today.

Transactions on Science and Technology, 2016

© Transactions on Science and Technology 2016 Introduction In 1978 the famous Merkle & Hellman (1... more © Transactions on Science and Technology 2016 Introduction In 1978 the famous Merkle & Hellman (1978) article was published, which described an open key (asymmetric) cryptosystem based on a concrete case of the knapsack problem (Martello & Toth, 1990). We can formulate it as follows: there is a knapsack of V volume and a set of } ,... , { 2 1 n b b b B  subjects, which have certain volumes. Our goal is to find such B Bi  subset of B set, for the elements of which the following equation is worked out:

EPiC series in computing, Jan 23, 2018

E-mail is one of the most widespread communication method in twenty first century. People daily g... more E-mail is one of the most widespread communication method in twenty first century. People daily get e-mails in their inboxes, including permanently increasing number of unwanted notifications (spam) too. The advanced e-mail service packs and antiviruses contain spam filtration software. Nevertheless, to classify e-mails as spam, fully depends on user, as information acceptable (or vital) for one consumer, may be a spam for another. Hence, it is crucial to have automatic spam filtration system for every individual user. The paper discuss the solution, a system that filters emails through consumers' parameters and gradually learns how to filter them accordingly. The system is based on multi-layer neural network, which uses logistic activation function, learns via tutor and counter-spread algorithm of mistakes (a.k.a. method of supervised learning, backward propagation of errors).

The work deals with the problems of creating the knowledge base using artificial conceptual intel... more The work deals with the problems of creating the knowledge base using artificial conceptual intelligence, offers the reasoning mechanisms on the basis of logics, founded on the base of alternative sets, and discusses the applications of the knowledge to solve the problems of pattern recognition.

The paper discusses the modified variant of Hill's algorithm that can be used in the modern b... more The paper discusses the modified variant of Hill's algorithm that can be used in the modern block ciphers. Keywords: Symmetrical block cipher, Hill's algorithm, The principle of confusion and diffusion.

EPiC Series in Computing

The application of e-mail is the most widespread communication method. The increased email number... more The application of e-mail is the most widespread communication method. The increased email number includes permanently increased amount of unwanted notifications (spam). The statistics claims that 80% of the traffic is spam that lags the internet traffic, consumes space on hard disc, and reduces the capacity of the network, not to mention time spent for email’s classification. The advanced E-mail service packs contain spam filtration program. Nevertheless, to classify the e-mails as spam fully depends on the consumers, as information acceptable (or vital) for one consumer, may be a spam for other. Hence, it is crucial to have automatic spam filtration system for every individual consumer.The paper discuss the solution, a learning system that filters emails through consumers’ parameters and gradually learn how to filter them accordingly. The system based on multi-layer neural network, which uses logistic activation function, learns via tutor and counter-spread algorithm of mistakes

This paper discusses the use of genetic algorithms to cryptanalysis. Namely, how to break up the ... more This paper discusses the use of genetic algorithms to cryptanalysis. Namely, how to break up the Vigenere cipher with the genetic algorithm and why it is impossible to break complete the cipher with this method today.

Transactions on Science and Technology, 2016

© Transactions on Science and Technology 2016 Introduction In 1978 the famous Merkle & Hellman (1... more © Transactions on Science and Technology 2016 Introduction In 1978 the famous Merkle & Hellman (1978) article was published, which described an open key (asymmetric) cryptosystem based on a concrete case of the knapsack problem (Martello & Toth, 1990). We can formulate it as follows: there is a knapsack of V volume and a set of } ,... , { 2 1 n b b b B  subjects, which have certain volumes. Our goal is to find such B Bi  subset of B set, for the elements of which the following equation is worked out: