Detecting Content Rating Violations in Android Applications: A Vision-Language Approach
This addresses the challenge of automated content rating verification for mobile app stores, which is an incremental improvement over existing methods.
The paper tackles the problem of verifying content ratings for Android apps by proposing a vision-language approach that predicts ratings and detects violations, achieving ~6% better accuracy than the state-of-the-art and identifying over 70 potential violations with a 34.5% removal rate for flagged apps.
Despite regulatory efforts to establish reliable content-rating guidelines for mobile apps, the process of assigning content ratings in the Google Play Store remains self-regulated by the app developers. There is no straightforward method of verifying developer-assigned content ratings manually due to the overwhelming scale or automatically due to the challenging problem of interpreting textual and visual data and correlating them with content ratings. We propose and evaluate a visionlanguage approach to predict the content ratings of mobile game applications and detect content rating violations, using a dataset of metadata of popular Android games. Our method achieves ~6% better relative accuracy compared to the state-of-the-art CLIP-fine-tuned model in a multi-modal setting. Applying our classifier in the wild, we detected more than 70 possible cases of content rating violations, including nine instances with the 'Teacher Approved' badge. Additionally, our findings indicate that 34.5% of the apps identified by our classifier as violating content ratings were removed from the Play Store. In contrast, the removal rate for correctly classified apps was only 27%. This discrepancy highlights the practical effectiveness of our classifier in identifying apps that are likely to be removed based on user complaints.