Membership Encoding for Deep Learning

Abstract

Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data and advanced learning algorithms. The resulting models are considered as intellectual property of the model owners and their copyright should be protected. Also, MLaaS needs to be trusted not to embed secret information about the training data into the model, such that it could be later retrieved when the model is deployed. In this paper, we present membership encoding for training deep neural networks and encoding the membership information, i.e. whether a data point is used for training, for a subset of training data. Membership encoding has several applications in different scenarios, including robust watermarking for model copyright protection, and also the risk analysis of stealthy data embedding privacy attacks. Our encoding algorithm can determine the membership of significantly redacted data points, and is also robust to model compression and fine-tuning. It also enables encoding a significant fraction of the training set, with negligible drop in the model's prediction accuracy. CCS CONCEPTS • Computing methodologies → Machine learning; • Security and privacy → Software and application security.

Node-Level Membership Inference Attacks Against Graph Neural Networks

“…Membership Inference Attack. Membership inference attacks aim at inferring membership of individual training sam-ples of a target model to which an adversary has black-box access through a prediction API [5,9,19,28,30,31,35,36,39,51]. Most of the existing attacks focus on deep learning models that are trained on sensitive data from the Euclidean space, such as images and texts.…”