# Detecting Content Rating Violations in Android Applications: A Vision-Language Approach

arXiv: https://arxiv.org/abs/2502.15739 · HTML: https://mlsanity.com/paper/2502.15739/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [Unified Contrastive Learning in Image-Text-Label Space](https://mlsanity.com/paper/2204.03610/) (2022)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [A Straightforward Framework For Video Retrieval Using CLIP](https://mlsanity.com/paper/2102.12443/) (2021)
- [Explaining CLIP's performance disparities on data from blind/low vision users](https://mlsanity.com/paper/2311.17315/) (2023)
- [Not Seen, Not Heard in the Digital World! Measuring Privacy Practices in Children's Apps](https://mlsanity.com/paper/2303.09008/) (2023)
- [A Multi-modal Neural Embeddings Approach for Detecting Mobile Counterfeit Apps: A Case Study on Google Play Store](https://mlsanity.com/paper/2006.02231/) (2020)
- [Detecting and Characterising Mobile App Metamorphosis in Google Play Store](https://mlsanity.com/paper/2407.14565/) (2024)

## Built on by (most cited first, 1 of 1)

- [QwenSafe: Multimodal Content Rating Description Identification via Preference-Aligned VLMs](https://mlsanity.com/paper/2605.20584/) (2026)

## Abstract (arXiv)

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.