Image-guided topic modeling for interpretable privacy classification

Predicting and explaining the private information contained in an image in human-understandable terms is a complex and contextual task. This task is challenging even for large language models. To facilitate the understanding of privacy decisions, we propose to predict image privacy based on a set of natural language content descriptors. These content descriptors are associated with privacy scores that reflect how people perceive image content. We generate descriptors with our novel Image-guided Topic Modeling (ITM) approach. ITM leverages, via multimodality alignment, both vision information and image textual descriptions from a vision language model. We use the ITM-generated descriptors to learn a privacy predictor, Priv$\times$ITM, whose decisions are interpretable by design. Our Priv$\times$ITM classifier outperforms the reference interpretable method by 5 percentage points in accuracy and performs comparably to the current non-interpretable state-of-the-art model.

Black-box Attacks on Image Activity Prediction and its Natural Language Explanations

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.