%Aigaion2 BibTeX export from Idiap Publications
%Tuesday 03 December 2024 06:13:17 PM

@INPROCEEDINGS{Baia_ICCVW_AROW_2023,
         author = {Baia, Alina Elena and Poggioni, Valentina and Cavallaro, Andrea},
       keywords = {Activity Prediction, Adversarial Examples, Explainable AI, Textual Explanation},
       projects = {Idiap},
          title = {Black-box Attacks on Image Activity Prediction and its Natural Language Explanations},
      booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
           year = {2023},
            url = {https://ieeexplore.ieee.org/document/10350643},
            doi = {10.1109/ICCVW60793.2023.00396},
       abstract = {Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual representations. Visual XAI methods have been shown to be vulnerable to white-box and gray-box adversarial attacks, with an attacker having full or partial knowledge of and access to the target system. As the vulnerabilities of multimodal XAI models have not been examined, in this paper we assess for the first time the robustness to black-box attacks of the natural language explanations generated by a self-rationalizing image-based activity recognition model. We generate unrestricted, spatially variant perturbations that disrupt the association between the predictions and the corresponding explanations to mislead the model into generating unfaithful explanations. We show that we can create adversarial images that manipulate the explanations of an activity recognition model by having access only to its final output.},
            pdf = {https://publications.idiap.ch/attachments/papers/2023/Baia_ICCVW_AROW_2023.pdf}
}