Securing Web User Privacy with Steganalysis of Images using Deep Learning
K Anuratha, J. Nandhini, Devadharshini Madhavan, A Harini, Pavethra Arulmani · 2022 7th International Conference on Communication and Electronics Systems (ICCES) · 2022
Nowadays, images are extensively used in all aspects of community because of their ease of understandability, like cyber forensics and research-based exploration. Tampering digital images in special fields maliciously, may change the information contained therein, form false information, and result in damage to society. Data security is very important when sensitive data is transmitted over the internet. Whenever a website is opened, there are a lot of advertisements displayed on the page. Although they don’t intrude on our browsing experience, some images may hide vicious data inside them by using steganography. Hackers have become proficient in embedding their harmful code inside images. As soon as the user clicks on the image, the hidden code starts to affect the host machine by running in the background without the knowledge of the user. Henceforth, this research work proposes a system by using Deep Learning (DL) to detect steganography (Blind Steganalysis). Convolutional Neural Networks (CNN) is used in our system to prognosticate the presence of steganography by providing an extension in the web browser. By testing our model, it’s inferred that the accuracy in finding hidden content in images shows good results. The proposed model has achieved an accuracy of 89 percentage.