# A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok

arXiv: https://arxiv.org/abs/2403.19717 · HTML: https://mlsanity.com/paper/2403.19717/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 83 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 17 of 17)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations](https://mlsanity.com/paper/2007.12342/) (2020)
- [The Bias Amplification Paradox in Text-to-Image Generation](https://mlsanity.com/paper/2308.00755/) (2023)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [A First Look at Deep Learning Apps on Smartphones](https://mlsanity.com/paper/1812.05448/) (2018)
- [Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Apps](https://mlsanity.com/paper/2002.07687/) (2020)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [On the use of automatically generated synthetic image datasets for benchmarking face recognition](https://mlsanity.com/paper/2106.04215/) (2021)
- [Smart at what cost? Characterising Mobile Deep Neural Networks in the wild](https://mlsanity.com/paper/2109.13963/) (2021)
- [Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps](https://mlsanity.com/paper/2101.04401/) (2021)
- [Understanding Real-world Threats to Deep Learning Models in Android Apps](https://mlsanity.com/paper/2209.09577/) (2022)
- [Cross-Language Binary-Source Code Matching with Intermediate Representations](https://mlsanity.com/paper/2201.07420/) (2022)
- [Smart App Attack: Hacking Deep Learning Models in Android Apps](https://mlsanity.com/paper/2204.11075/) (2022)
- [Uncovering Bias in Face Generation Models](https://mlsanity.com/paper/2302.11562/) (2023)
- [JuCify: A Step Towards Android Code Unification for Enhanced Static Analysis](https://mlsanity.com/paper/2112.10469/) (2021)

## Built on by (most cited first, 2 of 2)

- ["Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications](https://mlsanity.com/paper/2503.03927/) (2025)
- [Challenges and Future Directions in Agentic Reverse Engineering Systems](https://mlsanity.com/paper/2604.14317/) (2026)

## Abstract (arXiv)

Mobile apps have embraced user privacy by moving their data processing to the user's smartphone. Advanced machine learning (ML) models, such as vision models, can now locally analyze user images to extract insights that drive several functionalities. Capitalizing on this new processing model of locally analyzing user images, we analyze two popular social media apps, TikTok and Instagram, to reveal (1) what insights vision models in both apps infer about users from their image and video data and (2) whether these models exhibit performance disparities with respect to demographics. As vision models provide signals for sensitive technologies like age verification and facial recognition, understanding potential biases in these models is crucial for ensuring that users receive equitable and accurate services. We develop a novel method for capturing and evaluating ML tasks in mobile apps, overcoming challenges like code obfuscation, native code execution, and scalability. Our method comprises ML task detection, ML pipeline reconstruction, and ML performance assessment, specifically focusing on demographic disparities. We apply our methodology to TikTok and Instagram, revealing significant insights. For TikTok, we find issues in age and gender prediction accuracy, particularly for minors and Black individuals. In Instagram, our analysis uncovers demographic disparities in the extraction of over 500 visual concepts from images, with evidence of spurious correlations between demographic features and certain concepts.