In applied sciences there is a tendency to rely on terminology that is either ill-defined or applied inconsistently across areas of research and application domains. Examples in information assurance include the terms resilience, robustness and survivability, where there exists subtle shades of meaning between researchers. These nuances can result in confusion and misinterpretations of goals and results, hampering communication and complicating collaboration. In this paper, we propose security-related definitions for these terms. Using this terminology, we argue that research in these areas must consider the functionality of the system holistically, beginning with a careful examination of what we actually want the system to do. We note that much of the published research focuses on a single aspect of a system -availability -as opposed to the system's ability to complete its function without disclosing confidential information or, to a lesser extent, with the correct output. Finally, we discuss ways in which researchers can explore resilience with respect to integrity, availability and confidentiality.

Recent work in the computational modeling of visual attention has demonstrated that a purely bottom-up approach to identifying salient regions within an image can be successfully applied to diverse and practical problems from target recognition to the placement of advertisement. This paper proposes an application of a combination of computational models of visual attention to the image retrieval problem. We demonstrate that certain shortcomings of existing content-based image retrieval solutions can be addressed by implementing a biologically motivated, unsupervised way of grouping together images whose salient regions of interest (ROIs) are perceptually similar regardless of the visual contents of other (less relevant) parts of the image. We propose a model in which only the salient regions of an image are encoded as ROIs whose features are then compared against previously seen ROIs and assigned cluster membership accordingly. Experimental results show that the proposed approach works well for several combinations of feature extraction techniques and clustering algorithms, suggesting a promising avenue for future improvements, such as the addition of a top-down component and the inclusion of a relevance feedback mechanism.

Recent research on computational modeling of visual attention has demonstrated that a bottom-up approach to identifying salient regions within an image can be applied to diverse and practical problems for which conventional machine vision techniques have not succeeded in producing robust solutions. This paper proposes a new method for extracting regions of interest (ROIs) from images using models of visual attention. It is presented in the context of improving content-based image retrieval (CBIR) solutions by implementing a biologically-motivated, unsupervised technique of grouping together images whose salient ROIs are perceptually similar. In this paper we focus on the process of extracting the salient regions of an image. The excellent results obtained with the proposed method have demonstrated that the ROIs of the images can be independently indexed for comparison against other regions on the basis of similarity for use in a CBIR solution.

No abstract

No abstract