7
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Who's Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrieval

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR), while appearing nearly untouched to the human eye. This paper presents an analysis of adversarial queries for CBIR based on neural, local, and global features. We introduce an innovative neural image perturbation approach, called Perturbations for Image Retrieval Error (PIRE), that is capable of blocking neural-feature-based CBIR. To our knowledge PIRE is the first approach to creating neural adversarial examples for CBIR. PIRE differs significantly from existing approaches that create images adversarial with respect to CNN classifiers because it is unsupervised, i.e., it needs no labeled data from the data set to which it is applied. Our experimental analysis demonstrates the surprising effectiveness of PIRE in blocking CBIR, and also covers aspects of PIRE that must be taken into account in practical settings: saving images, image quality, image editing, and leaking adversarial queries into the background collection. Our experiments also compare PIRE (a neural approach) with existing keypoint removal and injection approaches (which modify local features). Finally, we discuss the challenges that face multimedia researchers in the future study of adversarial queries.

          Related collections

          Most cited references19

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Video Google: a text retrieval approach to object matching in videos

                Bookmark

                Author and article information

                Journal
                29 January 2019
                Article
                1901.10332
                d96dd383-cff2-4345-bac6-08df73a5fb0f

                http://creativecommons.org/licenses/by-nc-sa/4.0/

                History
                Custom metadata
                cs.CV cs.IR cs.MM

                Computer vision & Pattern recognition,Information & Library science,Graphics & Multimedia design

                Comments

                Comment on this article