Reverse engineering ML models from TikTok and Instagram
This is very clever; _A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok_, from University of Wisconsin-Madison and the Technical Unversity of Munich. TikTok and Insta both use local ML models running on users’ phones; by reverse engineering these APIs it’s possible to test them and experiment on their accuracy.
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.
(tags: tiktok instagram ml machine-learning accuracy testing reverse-engineering reversing mobile android)