%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 12:37:13 PM

@INPROCEEDINGS{Xompero_CVPRW_2024,
         author = {Xompero, Alessio and Bontonou, Myriam and Arbona, Jean-Michel and Benetos, Emmanouil and Cavallaro, Andrea},
       projects = {Idiap},
          month = jun,
          title = {Explaining models relating objects and privacy},
      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
           year = {2024},
            url = {https://xai4cv.github.io/assets/papers2024/P07.pdf},
       abstract = {Accurately predicting whether an image is private before
sharing it online is difficult due to the vast variety of content and the subjective nature of privacy itself. In this paper, we evaluate privacy models that use objects extracted
from an image to determine why the image is predicted as
private. To explain the decision of these models, we use
feature-attribution to identify and quantify which objects
(and which of their features) are more relevant to privacy
classification with respect to a reference input (i.e., no objects localised in an image) predicted as public. We show
that the presence of the person category and its cardinality is the main factor for the privacy decision. Therefore,
these models mostly fail to identify private images depicting documents with sensitive data, vehicle ownership, and
internet activity, or public images with people (e.g., an outdoor concert or people walking in a public space next to a
famous landmark). As baselines for future benchmarks, we
also devise two strategies that are based on the person presence and cardinality and achieve comparable classification
performance of the privacy models.},
            pdf = {https://publications.idiap.ch/attachments/papers/2024/Xompero_CVPRW_2024.pdf}
}