Block mode image encryption technique using two-fold operations based on chaos, MD5 and DNA rules

Rehman, Aqeel Ur; Xiao, Di; Kulsoom, Ayesha; Hashmi, Muntazim Abbas; Abbas, Syed Ali

doi:10.1007/s11042-018-6516-1

Cited by 35 publications

(25 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of machine learning algorithm has gained popularity in different fields of computing [43][44][45][46][47][48]. The range of scholars motivated to investigate prognosis and diagnosis using machine learning methods is progressively increasing.…”

Section: Related Workmentioning

confidence: 99%

Performance Analysis of Classification Algorithms on Birth Dataset

et al. 2020

Self Cite

View full text Add to dashboard Cite

Generating intuitions from data using data mining and machine learning algorithms to predict outcomes is useful area of computing. The application area of data mining techniques and machine learning is wide ranging including industries, healthcare, organizations, academics etc. A continuous improvement is witnessed due to an ongoing research, as seen particularly in healthcare. Several researchers have applied machine learning to develop decision support systems, perform analysis of dominant clinical factors, extraction of useful information from hideous patterns in historical data, making predictions and disease classification. Successful researches created opportunities for physicians to take appropriate decision at right time. In current study, we intend to utilize the learning capability of machine learning methods towards the classification of birth data using bagging and boosting classification algorithms. It is obvious that differences in living styles, medical assistances, religious implications and the region you live in collectively affect the residents of that society. This motive has encouraged the researchers to conduct studies at regional levels to comprehensively explore the associated medical factors that contribute towards complications among women during pregnancy. The current study is a comprehensive comparison of bagging and boosting classification algorithms performed on birth data collected from the government hospitals of city Muzaffarabad, Kashmir. The experimental tasks are carried out using caret package in R which is considered an inclusive framework for building machine learning models. Accuracy based results with different evaluation measures are presented. Bagging functions including Adabag and BagFda performed marginally better in terms of accuracy, precision and recall. Improvements are observed in comparison to previous study performed on same dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Performance Analysis of Classification Algorithms on Birth Dataset

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among them, the researchers proposed a new plan, and the confusion and coding techniques are completely different due to the method of sequencing the block code of the jamming used at the bit level after stirring and DNA coding. In this procedure, the MD5 hash function is applied to formulate hash digestion to modify the initial conditions for all used messy maps [23]. The researchers proposed a new algorithm referring to Robust Integrity Verification Algorithm (RIVA).…”

Section: Previous Workmentioning

confidence: 99%

A Novel Improvement With an Effective Expansion to Enhance the MD5 Hash Function for Verification of a Secure E-Document

Ali

Farhan

2020

IEEE Access

View full text Add to dashboard Cite

MD5 is a one-way cryptographic function used in various fields for maintaining data integrity. The application of a Hash function can provide much protection and privacy and subsequently reduce data usage. Most users are familiar with validating electronic documents based on a Hash function, such as the MD5 algorithm and other hash functions, to demonstrate the data integrity. There are many weaknesses of the current MD5 algorithm, mainly its failures and weaknesses against varying types of attacks, such as brute force attacks, rainbow table attacks, and Christmas attacks. Therefore, the method proposed in this paper enhances the MD5 algorithm by adding a dynamic variable length and a high efficiency that simulates the highest security available. Whereas the logistic system was used to encode ribonucleic acid (RNA) by generating a random matrix based on a new key that was created using the initial permutation (IP) tables used in the data encryption stander (DES) with the linear-feedback shift register (LFSR), this work proposes several structures to improve the MD5 hash function. The experimental results demonstrate its high resistance to hackers while maintaining a suitable duration. This paper discusses the design of a confident hash algorithm. This algorithm has characteristics that enable it to succeed in the field of digital authentication and data integrity.

show abstract

“…The plain I and encrypted image E with L intensities are divided into non-overlapped k blocks where E 1 , • • • , E k with every blocks has T number of pixels. We have randomly selected K number of blocks and used Equation (27) to compute the mean of local entropy of k blocks. In the simulation, K = 32 and T = 1936 are used.…”

Section: Information Entropy Analysismentioning

confidence: 99%

“…The DNA sequence based algorithms have properties of parallelism and info density like DNA molecules [20]- [26]. The researchers have made a clear dent in improving existing cryptosystems in terms of their robustness to text-attacks by using DNA sequencing [21], [23], [27]- [30]. The DNA based schemes being new and less mature has seen cracking due to low dimensionality of chaotic maps causing periodicity [24], [32], [33].…”

Section: Introductionmentioning

confidence: 99%

A Selective Cross-Substitution Technique for Encrypting Color Images Using Chaos, DNA Rules and SHA-512

et al. 2019

Self Cite

View full text Add to dashboard Cite

An innovative approach of selective encryption for color images is proposed that utilizes SHA-512 hash of plain image to modify initial conditions and control parameters of 1-Dimensional (1D) chaotic maps. The three channels (red, green and blue) of a color image are combined into 1D array and permute using sorted index of a pseudo-random sequence. The 1D permuted array is split into three sub-arrays, DNA encoding is applied on every pixel of each channel chaotically and then separate each DNA encoded channel into its Least Significant Bits (LSB) and Most Significant Bits (MSB). The substitution is carried out in two phases using addition and exclusive-or operations on MSB of each channel only. In 1 st phase, the DNA addition operation is applied on chaotically selected MSB of a pixel of one channel to LSB part of a pixel of other channel in a twisted fashioned named cross-substitution. The translated DNA bases from pseudo-random numbers are exclusive-or with cross substituted output to surge the complexity. The second substitution phase is accomplished by combining MSB part of a channel with randomly selecting LSB at pixel level. The novel algorithm is highly suitable for real time applications as it requires single round of permutation/substitution which can resist all possible statistical and differential attacks. The simulation results and analysis show that the proposed technique has the best quality output and highly efficient.

show abstract

Block mode image encryption technique using two-fold operations based on chaos, MD5 and DNA rules

Cited by 35 publications

References 38 publications

Performance Analysis of Classification Algorithms on Birth Dataset

Performance Analysis of Classification Algorithms on Birth Dataset

A Novel Improvement With an Effective Expansion to Enhance the MD5 Hash Function for Verification of a Secure E-Document

A Selective Cross-Substitution Technique for Encrypting Color Images Using Chaos, DNA Rules and SHA-512

Contact Info

Product

Resources

About