<![CDATA[The exchange of sensitive data via social media platforms faces dual challenges: the risk of third-party interception and distortion due to image compression. Conventional steganography methods based on Least Significant Bit (LSB) often fail to balance embedding capacity with visual quality and are vulnerable to statistical steganalysis attacks. This research proposes a hybrid steganography framework that integrates multidomain adaptive pixel selection and layered cryptographic security. The pixel selection method combines Canny Edge Detection, Local Binary Pattern (LBP), and Local Entropy to determine optimal Regions of Interest (ROI). Data security is reinforced through content encryption using Advanced Encryption Standard (AES-256) and pixel position scrambling using Arnold Cat Map (ACM). Validation was conducted on 100 images from the ALASKA2 and Dresden datasets. Experimental results demonstrate the system's superior performance in balancing quality and capacity under standard load, the system achieves an average Peak Signal-to-Noise Ratio (PSNR) of 77.85 dB and a Structural Similarity Index (SSIM) of 1.0000. Stress tests confirmed the system's scalability, accommodating a maximum capacity of 3.00 bpp while maintaining safe visual quality (PSNR 51.26 dB). Although the system is fragile against JPEG compression on public timelines, this characteristic is validated to function effectively as a tamper sensitivity feature to detect illegal manipulation. Therefore, this framework is recommended as a solution for secure covert communication via document transmission channels (file sharing) on social media, ensuring high confidentiality and data authenticity.]]>
Copyrights © 2026
