Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource Faculty Publications Conference Paper Faculty Publications- Conference Papers Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Creator An entity primarily responsible for making the resource Adithiya, Dhanush; Jayabalan, Bhuvana; Beaulah Soundarabai, P.; Augustin, Peter Title A name given to the resource Evaluating Generalization and Robustness of U-Net Based Image Steganography Date A point or period of time associated with an event in the lifecycle of the resource 01-01-2025 Source A related resource from which the described resource is derived Proceedings - 2025 International Conference on Transformative Computing Technologies, ICTCT 2025;pp.178-183 Identifier An unambiguous reference to the resource within a given context <a href="https://doi.org/10.1109/ICTCT69201.2025.00045" target="_blank" rel="noreferrer noopener">https://doi.org/10.1109/ICTCT69201.2025.00045</a> <br /><br /><a href="https://www.scopus.com/pages/publications/105037437357?origin=resultslist" target="_blank" rel="noreferrer noopener">https://www.scopus.com/pages/publications/105037437357?origin=resultslist</a> Coverage The spatial or temporal topic of the resource, the spatial applicability of the resource, or the jurisdiction under which the resource is relevant Adithiya D., Christ (Deemed to be) University, Department of Computer Science, Bangalore, India; Jayabalan B., Christ (Deemed to be) University, Department of Computer Science, Bangalore, India; Beaulah Soundarabai P., Christ (Deemed to be) University, Department of Computer Science, Bangalore, India; Augustin P., Christ (Deemed to be) University, Department of Computer Science, Bangalore, India Description An account of the resource This paper investigates the effectiveness and generalization ability of U-Net based image steganography models across multiple datasets, with comparisons to the classical Least Significant Bit (LSB) substitution method. Models were trained on STL-10, CIFAR-10, and Stanford Cars datasets and evaluated both in-distribution and on out-of-distribution internet images. Results show that the STL-10 model consistently achieved the best trade-off between imperceptibility and recovery quality, while the CIFAR-10 model failed to generalize due to its low resolution and limited diversity. Baseline experiments confirmed that LSB achieves extremely high PSNR and SSIM at low payloads, but suffers sharp increases in Bit Error Rate (BER) under higher payloads or even mild distortions such as JPEG compression and Gaussian noise. By contrast, the U-Net model provided more stable recovery and greater robustness, highlighting the advantages of learned feature embeddings over handcrafted substitution. These findings underscore the importance of dataset diversity and robustness testing in developing practical steganographic systems for real-world deployment. 2025 IEEE. Subject The topic of the resource Deep Learning; Generalization; Image Steganography; Robustness; U-Net Publisher An entity responsible for making the resource available Institute of Electrical and Electronics Engineers Inc. Relation A related resource ISBN: 979-833159195-3; Language A language of the resource English Type The nature or genre of the resource Conference paper Rights Information about rights held in and over the resource Restricted Access; Hardcopy may be available in the library Format The file format, physical medium, or dimensions of the resource online