Finding Ε and Δ of Traditional Disclosure Control Systems

Abstract

This paper analyzes the privacy of traditional Statistical Disclosure Control (SDC) systems under a differential privacy interpretation. SDCs, such as cell suppression and swapping, promise to safeguard the confidentiality of data and are routinely adopted in data analyses with profound societal and economic impacts. Through a formal analysis and empirical evaluation of demographic data from real households in the U.S., the paper shows that widely adopted SDC systems not only induce vastly larger privacy losses than classical differential privacy mechanisms, but, they may also come at a cost of larger accuracy and fairness.

Cite

Text

Das et al. "Finding Ε and Δ of Traditional Disclosure Control Systems." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I20.30204

Markdown

[Das et al. "Finding Ε and Δ of Traditional Disclosure Control Systems." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/das2024aaai-finding/) doi:10.1609/AAAI.V38I20.30204

BibTeX

@inproceedings{das2024aaai-finding,
  title     = {{Finding Ε and Δ of Traditional Disclosure Control Systems}},
  author    = {Das, Saswat and Zhu, Keyu and Task, Christine and Van Hentenryck, Pascal and Fioretto, Ferdinando},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {22013-22020},
  doi       = {10.1609/AAAI.V38I20.30204},
  url       = {https://mlanthology.org/aaai/2024/das2024aaai-finding/}
}