Arindam Sarkar

An adaptive neural network guided secret key based encryption through recursive positional modulo-2 substitution for online wireless communication (ANNRPMS)

In this paper, a neural network guided secret key based technique for encryption (ANNRPMS) has been proposed using recursive positional modulo-2 substitution for online transmission of data/information through wireless communication. In this approach both the communicating networks receive an indistinguishable input vector, produce an output bit and are trained based on the output bit. The dynamics of the two networks and their weight vectors are found to a novel experience, where the demonstrate networks synchronize to an identical time dependent weight vectors. This observable fact has been used to form a secured variable length secret-key using a public channel. The length of the key depends on the number of input and output neurons. The original plain text is encrypted using recursive positional modulo-2 substitution technique. The secret key also fabricated through encryption process in a cascaded manner. This intermediate cipher text is again encrypted to form the final cipher text through chaining and cascaded xoring of identical weight vector with the identical length intermediate cipher text block. If size of the last block of intermediate cipher text is less than the size of the key then this block is kept unchanged. Receiver will use identical weight vector for performing deciphering process for getting the recursive positional modulo-2 substitution encrypted cipher text and secret key for decoding. A session key based transmission has also been proposed using 161-bit key format of 14 different segments [7,8]. Parametric tests are done and results are compared in terms of Chi-Square test, response time in transmission with some existing classical techniques, which shows comparable results for the proposed system.

An adaptive genetic key based neural encryption for online wireless communication (AGKNE)

In this paper, a genetic secret key based technique for neural encryption (AGKNE) has been proposed for online transmission of data/information in wireless communication. In this method both the communicating party receive the similar input vector, generate an output bit and are trained based on the output bit. Length of the key depends on the number of input and output neurons. Synchronized identical weight vectors are used to create chromosomes pool. Genetic secret key is generated on calculating the fitness function, which is the hamming distance between two chromosomes. GA operators like crossover and mutation are also used to add elitism of chromosomes. Plain stream passes through recursive modulo 2-substitution operation to generate intermediate cipher which is again encrypted using neuro genetic key to form the 2nd level cipher stream. Finally, chaining and cascaded xoring of neural key with the identical length intermediate cipher text is done to generate the cipher. Receiver will use identical neural weight secret key for performing deciphering process for generating the neuro genetic encrypted cipher text and secret key for decoding. Finally modulo-2 secret key uses to generate plain text. A session key based transmission has also been proposed using 161-bit key format of 14 different segments [7]. Parametric tests are done and results are compared in terms of Chi-Square test, response time in transmission with some existing classical techniques, which shows comparable results for the proposed system.

An Adaptive Neural Network guided Random Block Length based Cryptosystem for online wireless communication (ANNRBLC)

In this paper an Adaptive Neural Network guided Random Block Length based Cryptosystem (ANNRBLC) has been proposed for online transmission of data/information through wireless communication. Both communicating networks receive an identical input vector, generate an output bit, networks are trained based on the bit, and as a result of this dynamics through adaptive weight vectors the networks synchronize to an identical time dependent weight vectors. This phenomenon is used to form a secured secret-key through a public channel. Three sub keys are generated during the process to encrypt string of random length (multiple of 64 blocks). Length of sub key 1, sub key 2, sub key 3 is 128 bit, 192 bit, and 256 bit respectively. Identical weight vectors are used to generate first sub key of 128 bit length. Subsequent sub keys are generated as intermediate steps of the technique using neural cryptosystem. A session key based transmission has also been proposed using 161 bit key format of 14 different segments [7,8]. Parametric tests are done and results are compared in terms of Chi-Square test, response time in transmission with some existing classical techniques, which shows comparable results for the proposed system.

Computational Intelligence Based Neural Session Key Generation on E-Health System for Ischemic Heart Disease Information Sharing

In this paper, session key exchange and authentication technique executing in parallel fashion using the fine tuning of Two Tier Neural Network in wireless communication has been proposed for secured information transmission. E-Health online transmission of any medical information needs cryptographic implementations. Any medical information related to the patients which need to be shared secretly between different authorized parties. This proposed technique can be merged with any digitized cardiological-based Expert System with patients’ data preservation. Ischemic Heart Disease (IHD) is a set of cardiovascular problems with decreased blood flow rate. It is mainly caused due to narrowing of coronary arteries due to plaque accumulation in the channel. ECG signal diagnosing IHD is being digitized for secured transmission purpose. In this proposed technique identical Two Tier Neural Network is used by the both patient and Cardiologist. They mould to evoke a fine tuning of synaptic weight based on learning rules depending on their output value. Finally tuned weight vector becomes the secret session key for that particular session. At the time of parallel key exchange procedure, key authentication technique is also performed simultaneously. Different types of parametric tests were carried out and outputs are being compared with few classical techniques, which show favorable results for the proposed system.

Energy Efficient Secured Sharing of Intraoral Gingival Information in Digital Way (EESS-IGI)

This paper presents a novel cryptographic scheme for sharing intraoral information secretly where key is used to encrypt the secret Gingivitis image and then the secret is shared among ‘\( n \)’ number of experts. Periodontal diseases are almost a frequent disease in human body. The early stage of gingival inflammations with gum bleeding is called Gingivitis. If this disease is not diagnosed properly then it spreads to advanced Periodontotitis. Secured online transmission for such intraoral images is more significant factor in the advanced medicinal domain. An intraoral image is partially shared with ‘\( n \)’ number of recipients including patient for better expert opinions by applying encryption algorithm. While transmitting such vital images, the patients’ confidential secrets are preserved in such a way that minimum ‘k’ number of recipients can only reconstruct without change of visual appearance. This scheme is valid for various types of Gingivitis with independent number of shares and threshold value. Different parametric tests have been done and results are compared with some existing classical techniques, which show comparable results for the proposed technique.

Comparative Analysis of Tree Parity Machine and Double Hidden Layer Perceptron Based Session Key Exchange in Wireless Communication

In this paper, a detail analysis of Tree Parity Machine (TPM) and Double Hidden Layer Perceptron (DHLP) based session key exchange tecchnique has been presented in terms of synchronization time, space complexity, variability of learning rules, gantt chart, total number of threads and security. TPM uses single hidden layer in their architecture and participated in mutual learning for producing the tuned weights as a session key. DHLP uses two hidden layers instead of single. Addition of this extra layer enhances the security of the key exchange protocol. Comparisons of results of both techniques has been presented along with detail analysis.

Hopfield Network Based Neural Key Generation for Wireless Communication (HNBNKG)

In this paper, a key generation and encryption/decryption technique based on Hopfield Neural network has been proposed for wireless communication. Hopfield Neural networks at both ends forms identical input vector, weight vector which in turn produces identical output vector which is used for forming secret-key for encryption/decryption. Using this secret-key, plain text is encrypted to form the cipher text. Encryption is performed by Exclusive-OR operation between plaintext and secret-key. Decryption is performed at the receiver through Exclusive-OR operation between cipher text and identical secret-key generated. Receiver regenerate the original message sent by the sender as encrypted stream. In HNBNKG technique sender and receiver never exchange secret-key. This technique ensured that, when message is transmitting between sender-receiver nobody can regenerate the message as no key is exchanged.

KSOFM Network Based Neural Key Generation for Wireless Communication

In this paper a single layer perceptron (KSOFM Network) based neural key generation for encryption/decryption for wireless communication has been proposed. Identical KSOFM network has been used in both sender and receiver side and the final output weight has been used as a secret key for encryption and decryption. The final output matrix of the KSOFM network is taken and the minimum value neuron in the matrix is considered as the secret key. Depending upon the input and output neuron, different keys has been generated for each session which helps to form secret session key. In sender side the plain text is encrypted with the secret key to form the cipher text done by the EX-OR operation between the secret key and the plain text. Receiver will use the same secret key to decrypt the cipher text to plane text. The secret key is not sent via any medium so it minimizes the man-in-the-middle attack. Moreover various tests are performed in terms of chi-square test, which shows comparable results with the said proposed system.

Neuro-key Generation Based on HEBB Network for Wireless Communication

In this paper a key generation technique for encryption/decryption, based on a single-layer perceptron network (Hebb Network), for wireless communication of information or data has been proposed. Two HEBB Neural networks have been used at both the sender and receiver ends. Both the networks have a Random Number Generator (RNG) that generates identical inputs at both ends. As both the networks are synchronized they generate same output pair for same input pair which is used as the secured secret key to encrypt the plain text through some reversible computation to form the cipher text. The receiver generate plain text by performing identical operation. The key is never transmitted during encoding across the network. This process ensures the integrity and confidentiality of a message transmitted via any medium as the secret key is unknown to any intruder thus imparts a potential solution to Man-in-the-middle attack.

Complete Binary Tree Architecture Based Triple Layer Perceptron Synchronized Group Session Key Exchange and Authentication in Wireless Communication (CBTLP)

In this paper, Triple Layer Perceptron harmonized one time session key exchange and authentication (CBTLP) has been proposed based on the structural design of complete binary tree. In this proposed technique 3 hidden layers are used in the architecture of the TLP to enhance the security. This proposed CBTLP scheme offers structure of complete binary tree. Group of parties can participate in TLP synchronization and key switch over process. In CBTLP scheme only O(log2 N) synchronization is needed for swap over the session key among N parties.