Journal Article10.1007/S11045-020-00739-8
Multiobjective evolutionary optimization techniques based hyperchaotic map and their applications in image encryption
Manjit Kaur,Dilbag Singh +1 more
79
TL;DR: A dual local search based multiobjective optimization (DLS-MO) is used to obtain the optimal parameters of a hyper-chaotic map and encryption factors and this approach provides better performance in comparison to existing competitive approaches.
read more
Abstract: Chaotic-based image encryption approaches have attracted great attention in the field of information security. The properties of chaotic maps such as randomness and sensitivity have given new ways to develop efficient encryption approaches. But chaotic maps require initial parameters to develop random sequences. The selection of these parameters is a tedious task. To obtain the optimal initial parameters, evolutionary optimization approaches have been utilized in image encryption. Therefore, in this paper, a hyper-chaotic map is optimized using a multiobjective evolutionary optimization approach. A dual local search based multiobjective optimization (DLS-MO) is used to obtain the optimal parameters of a hyper-chaotic map and encryption factors. Then, using optimal parameters, a hyper-chaotic map develops the secret keys. These secret keys are then used to perform permutation and diffusion on a plain image to develop the encrypted image. To perform encryption, permutation–permutation–diffusion–diffusion architecture is adopted for better confusion and diffusion. Experimental results show that the proposed approach provides better performance in comparison to existing competitive approaches.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Systematic Review of Security Vulnerabilities in Ethereum Blockchain Smart Contract
01 Jan 2022
TL;DR: A systematic review of the security vulnerabilities in the Ethereum blockchain is presented in this paper , where the main objective is to discuss Ethereum smart contract security vulnerabilities, detection tools, real life attacks and preventive mechanisms.
Research on the Natural Language Recognition Method Based on Cluster Analysis Using Neural Network
Guang Li,Fangfang Liu,Ashutosh Sharma,Osamah Ibrahim Khalaf,Youseef Alotaibi,Abdulmajeed Alsufyani,Saleh Alghamdi +6 more
TL;DR: A new method of structural modeling is utilized to generate the structured derivation relationship, thus completing the natural language knowledge extraction process of the object-oriented knowledge system.
Efficient 3D AlexNet Architecture for Object Recognition Using Syntactic Patterns from Medical Images
Shilpa Rani,Deepika Ghai,Sandeep Kumar,M. V. V. Prasad Kantipudi,Amal H. Alharbi,Mohammad Aman Ullah +5 more
TL;DR: The comparative analyses reveal that the proposed brain tumor classification model achieves significantly better performance than the existing models.
Spoken Language Identification Using Deep Learning.
TL;DR: In this article, the authors used the convolutional neural network (CNN) to detect languages out of English, French, Spanish, and German, Estonian, Tamil, Mandarin, Turkish, Chinese, Arabic, Hindi, Indonesian, Portugal, Japanese, Latin, Dutch, Portuguese, Pushto, Romanian, Korean, Russian, Swedish, Tamil and Thai, and Urdu.
Machine Learning-Based Fault Diagnosis of Self-Aligning Bearings for Rotating Machinery Using Infrared Thermography
TL;DR: A two-dimensional discrete wavelet transform has been applied for the decomposition of the thermal image and results reveal that the SVM outperformed LDA as well as KNN in classification of faults and performance assessment.
References
SMS-EMOA : Multiobjective selection based on dominated hypervolume
TL;DR: A steady-state EMOA is proposed that features a selection operator based on the hypervolume measure combined with the concept of non-dominated sorting, thereby focussing on interesting regions of the Pareto front.
2K
Finding collisions in the full SHA-1
Xiaoyun Wang,Yiqun Lisa Yin,Hongbo Yu +2 more
- 14 Aug 2005
TL;DR: This is the first attack on the full 80-step SHA-1 with complexity less than the 280 theoretical bound, and it is shown that collisions ofSHA-1 can be found with complexityLess than 269 hash operations.
On the derivation of a “Chaotic” encryption algorithm
TL;DR: This paper derives a “chaotic” function, and shows that it may be suitable for cryptographic use, in particular as a replacement for the one-time pad system.
1K
NPCR and UACI Randomness Tests for Image Encryption
Yue Wu,Joseph P. Noonan,Sos S. Agaian +2 more
- 01 Jan 2011
TL;DR: The question of whether a given NPCR/UACI score is sufficiently high such that it is not discernible from ideally encrypted images is answered by comparing actual NPCR and UACI scores with corresponding critical values.
1K
A faster algorithm for calculating hypervolume
TL;DR: An algorithm for calculating hypervolume exactly, the Hypervolume by Slicing Objectives (HSO) algorithm, that is faster than any that has previously been published and increases the utility of hypervolume, both as a metric for general optimization algorithms and as a diversity mechanism for evolutionary algorithms.