VStegNET: Video Steganography Networkusing Spatio-Temporal features andMicro-Bottleneck

Steganography is the practice of hiding a secret message in a cover message such thatthe cover stays indiscernible after hiding and only the intended recipients can extract thesecret from it. Traditional image steganography techniques hide the secret image intohigh-frequency regions of the cover images. These techniques typically result in lowerembedding ratios and easy detection. In this paper, we propose VStegNET, a videosteganography network that extracts spatio-temporal features using 3D-CNN and micro-bottleneck (Hourglass) which is the first of its kind in the literature of video steganog-raphy. The proposed network hidesM×N(RGB) secret video frames into same sizedcover video frames. We have trained our model onUCF 101 action recognitionvideodataset and evaluated its performance using various quantitative metrics (APD, PSNR,and SSIM) and compared it with previous the state-of-the-art. Furthermore, we have alsopresented a detailed analysis, supporting the proposal’s superiority over image steganog-raphy models. Finally, several standard steganalysis tools like StegExpose, SRNET, etc.have been used to justify the steganographic capabilities of VStegNET.