The widespread availability of image editing software makes editing and distributing images easy, complicating the ability to trust their content. Such images can be manipulated in forgery attacks to disseminate false propaganda, undermining their authenticity and originality. This paper presents a review focusing on the tamper localization and content recovery in fragile image watermarking. As a result, image authentication plays a crucial role in protecting the integrity of digital images. This review investigates the primary challenge encountered by the researcher in tamper localization and self-recovery such as limited space for embedding the recovery data. Another problem faced by researchers in image authentication and self-recovery is the presence of the tamper coincidence problem. This review also discusses the tamper coincidence problem in fragile watermarking. It occurs when the recovery data is missing because both the original block and another block for storing recovery data are tampered with. This study serves as a comprehensive reference for researchers, and the issue of tampering coincidence may significantly affect the recovered image quality. The existing methods are discussed for embedding authentication bits and recovery data to examine the overall watermarking performance. These findings have a potential solution for identifying the tampered region problems in fragile image watermarking.

Tracer Study is a mandatory aspect of accreditation assessment in Indonesia. The Indonesian Ministry of Education requires all Indonesia Universities to anually report graduate tracer study reports to the government. Tracer study is also needed by the University in evaluating the success of learning that has been applied to the curriculum. One of the things that need to be evaluated is the level of absorption of graduates into the working industry, so a machine learning model is needed to assist the University Officials in evaluating and understanding the character of its graduates, so that it can help determine curriculum policies. In this research, the researcher focuses on making a reliable machine learning model with a tracer study dataset format that has been determined by the Government of Indonesia. The dataset was obtained from the tracer study of Amikom University. In this study, SVM will be tested with several variants of the algorithm to handle imbalanced data. The study compared SMOTE, SMOTE-ENN, and SMOTE-Tomek combined with SVM to detect the employability of graduates. The test was carried out with K-Fold Cross Validation, with the highest accuracy and precision results produced by SMOTE-ENN SVM model by value of 0.96 and 0.89.

This paper proposes a new block mapping technique for image authentication and self-recovery designed to avoid the tamper coincidence problem called the AuSR3. The tamper coincidence problem can arise when modifications to an image affect the original block and its recovery data, resulting in the inability to recover the tampered region of the image. The new block mapping technique ensures that the recovery data of a block is embedded into the most distant location possible, minimizing the tamper coincidence problem. In addition, the improved LSB shifting algorithm is employed to embed the watermark data consisting of authentication and recovery data. The experimental result shows that the AuSR3 can produce high-quality watermarked images across various datasets with average PSNR values of 46.2 dB, which improved by 2.1 dB compared to the LSB replacement technique. The new block mapping technique avoids the tamper coincidence problem by up to 25% tampering rates. It contributes to the high-quality recovered image with a PSNR and SSIM value of 39.10 dB and 0.9944, respectively, on a 10% tampering rate on the USC-SIPI dataset.