An Image Encryption Scheme Based on DNA Computing and Multiple Chaotic Systems

Abstract

A number of techniques for securing plaintext, images and video frames have been developed in cryptography using jointly DNA computing and Chaos Theory. With the advancement of DNA/quantum computing, the threats of security breaches to information have an increasing possibility. In this paper, we propose a symmetric encryption algorithm for color images by extending the current encryption/decryption techniques. Our encryption algorithm is based on three chaotic systems (PWLCM, Lorenz and 4D Lorenz-type), a Secure Hash Algorithm, a scrambler, a chaotic generator and DNA sequence based Linear Feedback Shift Register. We introduce multilevel security to increase the degree of diffusion and confusion. Through experiments, we present security analysis for key irreproducibility and sensitivity, Gray Level Co-occurrence Matrix based analysis, maximum deviation, irregular deviation, entropy, histogram, variance and correlation, number of pixel change rate, unified average cipher intensity, known/chosenplaintext attacks, mean absolute error, robustness against noises of various types using PSNR and occlusion attacks. It is demonstrated that mostly our proposed encryption algorithm has enhanced performance as compared to contemporary works in information security, while comparable in other cases. INDEX TERMS Bit scrambling, chaotic generator, DNA sequence based linear feedback shift register, DNA encoding, hypechaos, secure hash algorithm.

Particle Swarm Optimization Based Highly Nonlinear Substitution-Boxes Generation for Security Applications

“…The encryption speed performance is compared with other image encryption schemes in Table 8. The proposed encryption scheme offers great encryption quality and encryption time is considerably shorter than many of its contemporary schemes investigated in [56,[60][61][62][63][64][65]. Thus, the proposed S-boxes based encryption scheme is faster compared to many recent competitor schemes which make it suitable for real-time image encryption applications.…”

Synchronization of Chaotic System Using a Brain-Imitated Neural Network Controller and Its Applications for Secure Communications

“…An actually random image (RI) provides an even distribution of pixel intensities in the range [0, 255], and the entropy value for an ideal RI is 8. Table IV shows the entropy results, which are computed by different methods such as DNA method [40], hash keying method [41], ciphertext diffusion in crisscross pattern [42], an improved and enhanced method based on hyperchaos [43], DNA encoding method [44], hyper-chaotic and DNA sequences method [45]. It can be observed that their values are approximately 8, so the encrypted image is of maximum randomness leading to the confidentiality of the data.…”

“…[40] Hash keying method [41] Ciphertext diffusion in crisscross pattern [42] An improved and enhanced method based on hyperchaos [43] DNA encoding method [44] Hyper-chaotic and DNA sequences method [ In this section, we respectively use 512 512  pairs of two nearby pixels in three directions (diagonal, horizontal, and vertical) of the original and encrypted images to check the correlation between two nearby pixels of an encrypted image, the below equation can be used [19]: [40] Ciphertext diffusion in crisscross pattern [42] An improved and enhanced method based on hyperchaos [43] DNA encoding method [44] Hyper-chaotic and DNA sequences method The correlation distributions between the encrypted and original images for Lena, baboon, and peppers are respectively shown in Figs. 19-21. Our method efficiently reduces the correlation of pixels compared to DNA method [40], ciphertext diffusion in crisscross pattern [42], an improved and enhanced method based on hyperchaos [43], DNA encoding method [44], and hyperchaotic and DNA sequences method [45]. The correlation coefficients between two nearby pixels of the original images are calculated in Table V, which shows that two nearby pixels of the original images are completely different.…”

“…The PSNR between the proposed method and the former methods is presented in Table VIII. Analysis results indicate that our method achieves better performance and quality than DNA method [40] and robust and lossless color image encryption method [46]. This study uses number of pixels change rate (NPCR) and unified average changing intensity (UACI) to test the resisting differential attack performance of the proposed encryption method.…”

“…[37]. The NPCR and UACI results for Lena, Peppers and Baboon images are respectively shown in Table IX [40] Robust and lossless color image encryption method [46] Our method DNA method [40] Robust and lossless color image encryption method [ In reality, images are attacked by noise during communication, and using the encrypted image is a defense against that attack. In this section, the Lena image is used as a test image for the proposed method.…”