Adversarial representation learning for synthetic replacement of private attributes

John Martinsson, Edvin Listo Zec, Daniel Gillblad, Olof Mogren

Keywords: Deep learning, privacy, generative adversarial networks

Abstract: Data privacy is an increasingly important aspect of many real-world big data analytics tasks. Data sources that contain sensitive information may have immense potential which could be unlocked using privacy enhancing transformations, but current methods often fail to produce convincing output. Furthermore, finding the right balance between privacy and utility is often a tricky trade-off. In this work, we propose a novel approach for data privatization, which involves two steps: in the first step, it removes the sensitive information, and in the second step, it replaces this information with an independent random sample. Our method builds on adversarial representation learning which ensures strong privacy by training the model to fool an increasingly strong adversary. While previous methods only aim at obfuscating the sensitive information, we find that adding new random information in its place strengthens the provided privacy and provides better utility at any given level of privacy. The result is an approach that can provide stronger privatization on image data, and yet be preserving both the domain and the utility of the inputs, entirely independent of the downstream task.

One-sentence Summary: Explores if realistic synthetic replacement of sensitive attributes leads to stronger privacy, and empirically studies the privacy vs. utility trade-off for learned privacy preserving image transformations.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=c2nfAcHCJq