# On Privacy and Confidentiality of Communications in Organizational Graphs

arXiv: https://arxiv.org/abs/2105.13418 · HTML: https://mlsanity.com/paper/2105.13418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 56 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Gmail Smart Compose: Real-Time Assisted Writing](https://mlsanity.com/paper/1906.00080/) (2019)
- [Practical Differentially Private Top-k Selection with Pay-what-you-get Composition](https://mlsanity.com/paper/1905.04273/) (2019)
- [Privacy in Social Media: Identification, Mitigation and Applications](https://mlsanity.com/paper/1808.02191/) (2018)
- [A Survey of Location Prediction on Twitter](https://mlsanity.com/paper/1705.03172/) (2017)
- [Pufferfish Privacy Mechanisms for Correlated Data](https://mlsanity.com/paper/1603.03977/) (2016)
- [Differentially Private Set Union](https://mlsanity.com/paper/2002.09745/) (2020)
- [Recursive Mechanism: Towards Node Differential Privacy and Unrestricted Joins [Full Version, Draft 0.1]](https://mlsanity.com/paper/1304.4795/) (2013)
- [Blowfish Privacy: Tuning Privacy-Utility Trade-offs using Policies](https://mlsanity.com/paper/1312.3913/) (2013)
- [Inferential Privacy Guarantees for Differentially Private Mechanisms](https://mlsanity.com/paper/1603.01508/) (2016)
- [Efficient Lipschitz Extensions for High-Dimensional Graph Statistics and Node Private Degree Distributions](https://mlsanity.com/paper/1504.07912/) (2015)
- [walk2friends: Inferring Social Links from Mobility Profiles](https://mlsanity.com/paper/1708.08221/) (2017)

## Abstract (arXiv)

Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality is distinct from privacy in an enterprise context, and aims to formulate an approach to preserving confidentiality while leveraging principles from differential privacy. The goal is to perform machine learning tasks, such as learning a language model or performing topic analysis, using interpersonal communications in the organization, while not learning about confidential information shared in the organization. Works that apply differential privacy techniques to natural language processing tasks usually assume independently distributed data, and overlook potential correlation among the records. Ignoring this correlation results in a fictional promise of privacy. Naively extending differential privacy techniques to focus on group privacy instead of record-level privacy is a straightforward approach to mitigate this issue. This approach, although providing a more realistic privacy-guarantee, is over-cautious and severely impacts model utility. We show this gap between these two extreme measures of privacy over two language tasks, and introduce a middle-ground solution. We propose a model that captures the correlation in the social network graph, and incorporates this correlation in the privacy calculations through Pufferfish privacy principles.