@inproceedings{326efe61a8f44428bce5aaf26ec7bf01,
title = "Processing text for privacy: an information flow perspective",
abstract = "The problem of text document obfuscation is to provide an automated mechanism which is able to make accessible the content of a text document without revealing the identity of its writer. This is more challenging than it seems, because an adversary equipped with powerful machine learning mechanisms is able to identify authorship (with good accuracy) where, for example, the name of the author has been redacted. Current obfuscation methods are ad hoc and have been shown to provide weak protection against such adversaries. Differential privacy, which is able to provide strong guarantees of privacy in some domains, has been thought not to be applicable to text processing. In this paper we will review obfuscation as a quantitative information flow problem and explain how generalised differential privacy can be applied to this problem to provide strong anonymisation guarantees in a standard model for text processing.",
keywords = "Author anonymity, Author obfuscation, Information flow, Privacy, Probabilistic semantics, Refinement, Text processing",
author = "Natasha Fernandes and Mark Dras and Annabelle McIver",
year = "2018",
month = jan,
day = "1",
doi = "10.1007/978-3-319-95582-7_1",
language = "English",
isbn = "9783319955810",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer, Springer Nature",
pages = "3--21",
editor = "Klaus Havelund and Jan Peleska and Bill Roscoe and {de Vink}, Erik",
booktitle = "Formal Methods",
address = "United States",
note = "22nd International Symposium on Formal Methods, FM 2018 Held as Part of the Federated Logic Conference, FloC 2018 ; Conference date: 15-07-2018 Through 17-07-2018",
}