According to various worldwide statistics, most car accidents occur solely due to human error. The person driving a car needs to be alert, especially when travelling through high traffic volumes that permit high-speed transit since a slight distraction can cause a fatal accident. Even though semiautomated checks, such as speed detecting cameras and speed barriers, are deployed, controlling human errors is an arduous task. The key causes of driver’s distraction include drunken driving, conversing with co-passengers, fatigue, and operating gadgets while driving. If these distractions are accurately predicted, the drivers can be alerted through an alarm system. Further, this research develops a deep convolutional neural network (deep CNN) models for predicting the reason behind the driver’s distraction. The deep CNN models are trained using numerous images of distracted drivers. The performance of deepCNNmodels, namely theVGG16,ResNet, and Xception network, is assessed based on the evaluation metrics, such as the precision score, the recall/sensitivity score, the F1 score, and the specificity score. The ResNet model outperformed all other models as the best detection model for predicting and accurately determining the drivers’ activities.

Performance Comparison of Deep CNN Models for Detecting Driver’s Distraction

Steganography and steganalysis is a relatively new-fangled scientific discipline in security systems and digital forensics, respectively, but one that has matured greatly over the past two decades. In any specialism of human endeavour, it is imperative to periodically pause and review the state of the discipline for what has been achieved till date. This article scrutinizes where the discipline of steganography and steganalysis at this point in time in context to the common user and new researchers in terms of current trends. Also, what has been accomplished in order to critically examine what has been done well and what ought to be done better. The state-of-the-art techniques for steganography and steganalysis (image and video) have been deliberated for the last 5 years literature. Further, the paper also takes stock the dataset and tools available for multimedia steganography and steganalysis with the examples where steganography has been used in real-life. It is a corpus of the author’s opinion and the viewpoints of different other researchers and practitioners, working in this discipline. Additionally, experiments were done using image steganography techniques to analyse the recent trends. This survey is intended to provide a complete guide for common people and new researchers and scholars approaching this field, sight on the existing and the future of steganography and steganalysis.

Steganography and Steganalysis (in digital forensics): a Cybersecurity guide

The amount of data exchanged via the Internet is increasing nowadays. Hence, data security is termed as a serious issue while communication of data is processed over the Internet. Everyone needs th...

Analysis of various data security techniques of steganography: A survey

A fast and secure public-key image encryption scheme based on Mordell elliptic curves

Image encryption and steganography techniques are receiving a lot of interest and investigations due to their high importance in multimedia communication systems. A novel highly efficient image encryption and steganography technique are presented in this paper. For the first time, the proposed technique uses hybrid DNA encoding and Choquet's Fuzzy Integral sequences. At first, a confused version of the image, using a simple chaotic map, is encoded using DNA's bases. Four coded images are generated using the four DNA bases, namely AT, CG, GC, and TA. Parallel to that, a Choquet's fuzzy Integral sequence is generated and DNA encoded similarly to obtain four pseudo-random sequences. Secondly, the resulting four fuzzy/DNA sequences are used to diffuse the four DNA encoded images using the complementary DNA XOR rule, according to certain control code. Finally, the wavelet fusion algorithm is then used to fuse the resulting four fuzzy-DNA encoded images, to get the encrypted image. For added security, a new steganography approach is used. In particular, the encrypted image is divided into four sub-images, each of which is hidden in a different carrier image selected from a known group of carrier images according to a given key. The simulation results and security analysis confirmed the efficiency of the proposed image encryption algorithm as well as the steganography approach used for enhanced security. Ten different images with a size of 256 x 256 are used to test the proposed method. The results show that the proposed algorithm has a higher key sensitivity. The pixel correlation coefficient values are very small (between 5.3220e-04 and 0.0011 horizontally, between 8.7670e-04 and 0.0022 vertically and between 0.0002 and 0.0045 diagonally). Furthermore, the measured information entropy of the encrypted images is between 7.9970 and 7.9979 which are very close to the ideal value of 8. Additionally, the measured unified average changing intensity and number of pixels change rate values take the values between 33.46 and 33.39 and between 99.61 and 99.64, respectively, which are again closed to the ideal values. The steganography test shows that the hidden encrypted images are almost invisible at high values of SNR and are characterized by good NCC values under different types of attacks. The performance of the new proposed algorithm is proved to overcomes many other previously published image encryption techniques.

A New Fuzzy-DNA Image Encryption and Steganography Technique

Image steganography is a technology that hides sensitive information into an image. The traditional image steganography method tends to securely embed secret information in the host image so that the payload capacity is almost ignored and the steganographic image quality needs to be improved for the Human Visual System(HVS). Therefore, in this work, we propose a new high capacity image steganography method based on deep learning. The Discrete Cosine Transform(DCT) is used to transform the secret image, and then the transformed image is encrypted by Elliptic Curve Cryptography(ECC) to improve the anti-detection property of the obtained image. To improve steganographic capacity, the SegNet Deep Neural Network with a set of Hiding and Extraction networks enables steganography and extraction of full-size images. The experimental results show that the method can effectively allocate each pixel in the image so that the relative capacity of steganography reaches 1. Besides, the image obtained using this steganography method has higher Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity Index(SSIM) values, reaching 40dB and 0.96, respectively.

/pdf/a-new-high-capacity-image-steganography-method-combined-with-3telmo3yfu.pdf

A New High Capacity Image Steganography Method Combined With Image Elliptic Curve Cryptography and Deep Neural Network

The traditional cover modification steganography method only has low steganography ability. We propose a steganography method based on the convolutional neural network architecture (Xception) of deep separable convolutional layers in order to solve this problem. The Xception architecture is used for image steganography for the first time, which not only increases the width of the network, but also improves the adaptability of network expansion, and adds different receiving fields to carry out multi-scale information in it. By introducing jump connections, we solved the problems of gradient dissipation and gradient descent in the Xception architecture. After cascading the secret image and the mask image, high-quality images can be reconstructed through the network, which greatly improves the speed of steganography. When hiding, only the secret image and the cover image are cascaded, and then the secret image can be embedded in the cover image through the hidden network in order to obtain the secret image. After extraction, the secret image can be reconstructed by bypassing the secret image through the extraction network. The results show that the results that are obtained by our model have high peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), and the average high load capacity is 23.96 bpp (bit per pixel), thus realizing large-capacity image steganography surgery.

High-Capacity Image Steganography Based on Improved Xception.

Image-to-image steganography is hiding one image in another image. However, hiding two secret images into one carrier image is a challenge today. The application of image steganography based on deep learning in real-life is relatively rare. In this paper, a new Steganography Convolution Neural Network (SteganoCNN) model is proposed, which solves the problem of two images embedded in a carrier image and can effectively reconstruct two secret images. SteganoCNN has two modules, an encoding network, and a decoding network, whereas the decoding network includes two extraction networks. First, the entire network is trained end-to-end, the encoding network automatically embeds the secret image into the carrier image, and the decoding network is used to reconstruct two different secret images. The experimental results show that the proposed steganography scheme has a maximum image payload capacity of 47.92 bits per pixel, and at the same time, it can effectively avoid the detection of steganalysis tools while keeping the stego-image undistorted. Meanwhile, StegaoCNN has good generalization capabilities and can realize the steganography of different data types, such as remote sensing images and aerial images.

https://www.mdpi.com/1099-4300/22/10/1140/pdf

Mengxiao Gou

Papers

A New High Capacity Image Steganography Method Combined With Image Elliptic Curve Cryptography and Deep Neural Network

High-Capacity Image Steganography Based on Improved Xception.

SteganoCNN: Image Steganography with Generalization Ability Based on Convolutional Neural Network.