The structure of human society is always profoundly affected by the developments happening in the domain of communication. Data security and privacy have always been a concern in the ongoing communication revolution. The Department of Computer Science and Engineering is glad to inform you that the paper, “An Efficient Spatial Transformation-based Entropy Retained Reversible Data Hiding Scheme in Encrypted Images,” has been published by Dr V M Manikandan, Assistant Professor, and his PhD student Mr Shaiju Panchikkil in “Optik Journal” with an impact factor of 2.443.

Abstract of the research

A critical issue with the current communication revolution is data security and privacy, which is an inevitable part of trustworthiness in the communication system. Hence, the applicability of the Reversible Data Hiding schemes (RDH) in this scenario is encouraging and critical, like medical image communication, satellite image transmission, etc. Earlier, we explored Arnold transform in one of our previous works to hide the secret data that uses the Convolutional Neural Network (CNN) model to design a complete RDH scheme. The proposed scheme follows a statistical approach to support recovering the cover image and the embedded information. This approach proves advantageous over the previous work following its computational capability. The scheme designed can retain the entropy of the encrypted images even after embedding the additional information, complementing the security of the encryption algorithm.

Explanation of the research

The research focuses on hiding information in an encrypted image and transmitting it to the receiver. Earlier, the researchers used the Arnold transform-based image scrambling algorithm to facilitate the data hiding. But at the receiver end, they have used a convolutional neural network model, which acts as a binary classifier to recover the image properly after extracting the hidden information. The researchers had a few overheads over there, like training the model and then sharing the same with the receiver to recover the original image efficiently. To overcome these overheads, they analysed the correlation of neighboring pixels and introduced a statistical measure at the receiver end to recover the exact image.

Social implications of the research

One of the various social implications of the research is an application concerning patient treatment. In a general scenario, during the covid 19 pandemic, people make an online consultation with the doctor by uploading their medical images. If the doctor wants to take a specialist’s opinion, he should send this image and the diagnosis report via a communication medium. The research team’s approach is meaningful in this aspect. The original image is initially encrypted, which makes it unreadable. The diagnosis report information is hidden over the encrypted image. Hence the doctor needs to send only a single file to the specialist. It is also difficult for an external agent or an unauthorized party to decode the report and the image as it is encrypted. Now it is essential to regain the original quality of the recovered image, as any degradation in the quality of the recovered image can lead to a wrong diagnosis. Hence, they have designed the recovery module carefully to extract all the hidden information and recover the original image without compromising its quality.

The researchers are in constant collaboration with Professor Yu-Dong Zhang from the University of Leicester, University Road, Leicester, LE1 7RH, UK, to introduce new strategies to elevate the embedding capacity from the current level without negotiating the quality of the recovered image.

The Department of Computer Science and Engineering is pleased to announce the publication of three different patent applications from the department. The patent applications were submitted by the BTech students; Mr Kandala Sree Rama Murthy, Ms Padmaja Buggaveeti, Ms Yadlapalli Sai Harshini, Mr Jagruth K, Ms Shikha Chauhan, and Ms Ravi Srihitha under the guidance of Assistant Professor Dr V M Manikandan. They are making the institution proud with their passion and enthusiasm for the research domain.

The invention of a new scheme that will help to retrieve relevant videos from a large pool based on the given keyword is an impressive concept with societal relevance. Dr V M Manikandan and BTech students; Ms Yadlapalli Sai Harshini, Mr Jagruth K, Ms Shikha Chauhan, and Ms Ravi Srihitha got their patent application titled A novel video retrieval system and method based on textual information (application number: 202241002653) published.

The conventional video retrieval system uses the metadata to retrieve the appropriate videos. The new scheme processes the video and identifies the text information within the video, which will be compared with the given keyword. They introduced a scene change detection technique to select the frames for further processing in the new system to reduce the overall processing time.

The new scheme will help to retrieve appropriate educational videos from a large video pool based on the given keyword. The processing time is a significant concern in the scheme proposed. The researchers’ future work will be focused on improving the time complexity of the scheme.

The other research team invented a prediction error histogram shifting-based approach to hide secret messages in a cover image. The patent application submitted by Dr V M Manikandan and Third-year BTech-CSE Student, Ms Padmaja Buggaveeti, is titled A reversible data hiding system and method for image transmission (application number: 202241002654). The method ensures the lossless recovery of the original image during data extraction. The researchers considered the overflow issues in the histogram shifting approach and proposed an efficient method to handle this.

Reversible Data Hiding (RDH) provides a way to embed some data in a selected image so that in the future, the hidden data can be extracted along with the recovery of the original image. The new RDH scheme  invented by the researchers can be used in the healthcare sector to embed patient reports in medical images, or cloud service providers can use it to embed metadata in the digital data. Their future work will focus on designing and implementing robust reversible data hiding schemes capable of resisting attacks.

A system to facilitate secure transmission of an image along with embedded text (application number: 202241005221) is the third patent application that got published and was submitted by Dr V M Manikandan and Final year B.Tech-CSE Student Mr Kandala Sree Rama Murthy. The researchers invented a method to embed a message into a selected image during the image encryption process, which provides secure transmission of messages. The receiver will be able to extract the hidden message during decryption. The presented method is useful in medical image transmission to store patient details in the medical image.

The transmission of medical images and health reports from one hospital to another is widespread in the healthcare sector. Hospitals may want to handle many medical images and health reports every day and ensuring the one-to-one correspondence between them is a tedious task. The invented method will help embed health reports in medical images during encryption. The encrypted medical images (embedded with health reports) can be transmitted securely. The receiver will be able to extract the hidden message after medical image decryption. The researchers’ future work will focus on improving the invented method’s embedding capacity so that lengthy reports can be embedded into the medical images.