Advancement in information technology is playing an increasing role in the use of information systems comprising relational databases. These databases are used effectively in collaborative environments for information extraction; consequently, they are vulnerable to security threats concerning ownership rights and data tampering. Watermarking is advocated to enforce ownership rights over shared relational data and for providing a means for tackling data tampering. When ownership rights are enforced using watermarking, the underlying data undergoes certain modifications; as a result of which, the data quality gets compromised. Reversible watermarking is employed to ensure data quality along-with data recovery. However, such techniques are usually not robust against malicious attacks and do not provide any mechanism to selectively watermark a particular attribute by taking into account its role in knowledge discovery. Therefore, reversible watermarking is required that ensures; (i) watermark encoding and decoding by accounting for the role of all the features in knowledge discovery; and, (ii) original data recovery in the presence of active malicious attacks. In this paper, a robust and semi-blind reversible watermarking (RRW) technique for numerical relational data has been proposed that addresses the above objectives. Experimental studies prove the effectiveness of RRW against malicious attacks and show that the proposed technique outperforms existing ones.

Recently, a significant amount of interest has been developed in motivating physicians to use e-health technology (especially Electronic Medical Records (EMR) systems). An important utility of such EMR systems is: a next generation of Clinical Decision Support Systems (CDSS) will extract knowledge from these electronic medical records to enable physicians to do accurate and effective diagnosis. It is anticipated that in future such medical records will be shared through cloud among different physicians to improve the quality of health care. Therefore, right protection of medical records is important to protect their ownership once they are shared with third parties. Watermarking is a proven well-known technique to achieve this objective. The challenges associated with watermarking of EMR systems are: 1) some fields in EMR are more relevant in the diagnosis process; as a result, small variations in them could change the diagnosis, and 2) a misdiagnosis might not only result in a life threatening scenario but also might lead to significant costs of the treatment for the patients. The major contribution of this paper is an information-preserving watermarking scheme to address the above-mentioned challenges. We model the watermarking process as a constrained optimization problem. We demonstrate, through experiments, that our scheme not only preserves the diagnosis accuracy but is also resilient to well-known attacks for corrupting the watermark. Last but not least, we also compare our scheme with a well-known threshold-based scheme to evaluate relative merits of a classifier. Our pilot studies reveal that-using proposed information-preserving scheme-the overall classification accuracy is never degraded by more than 1 percent. In comparison, the diagnosis accuracy, using the threshold-based technique, is degraded by more than 18 percent in a worst case scenario.

The large datasets are being mined to extract hidden knowledge and patterns that assist decision makers in making effective, efficient, and timely decisions in an ever increasing competitive world. This type of “knowledge-driven” data mining activity is not possible without sharing the “datasets” between their owners and data mining experts (or corporations); as a consequence, protecting ownership (by embedding a watermark) on the datasets is becoming relevant. The most important challenge in watermarking (to be mined) datasets is: how to preserve knowledge in features or attributes? Usually, an owner needs to manually define “Usability constraints” for each type of dataset to preserve the contained knowledge. The major contribution of this paper is a novel formal model that facilitates a data owner to define usability constraints-to preserve the knowledge contained in the dataset-in an automated fashion. The model aims at preserving “classification potential” of each feature and other major characteristics of datasets that play an important role during the mining process of data; as a result, learning statistics and decision-making rules also remain intact. We have implemented our model and integrated it with a new watermark embedding algorithm to prove that the inserted watermark not only preserves the knowledge contained in a dataset but also significantly enhances watermark security compared with existing techniques. We have tested our model on 25 different data-mining datasets to show its efficacy, effectiveness, and the ability to adapt and generalize.

Image classification is a core field in the research area of image processing and computer vision in which vehicle classification is a critical domain. The purpose of vehicle categorization is to formulate a compact system to assist in real-world problems and applications such as security, traffic analysis, and self-driving and autonomous vehicles. The recent revolution in the field of machine learning and artificial intelligence has provided an immense amount of support for image processing related problems and has overtaken the conventional, and handcrafted means of solving image analysis problems. In this paper, a combination of pre-trained CNN GoogleNet and a nature-inspired problem optimization scheme, particle swarm optimization (PSO), was employed for autonomous vehicle classification. The model was trained on a vehicle image dataset obtained from Kaggle that has been suitably augmented. The trained model was classified using several classifiers; however, the Cubic SVM (CSVM) classifier was found to outperform the others in both time consumption and accuracy (94.8%). The results obtained from empirical evaluations and statistical tests reveal that the model itself has shown to outperform the other related models not only in terms of accuracy (94.8%) but also in terms of training time (82.7 s) and speed prediction (380 obs/sec).