Natasha Fernandes

Ms. Natasha Fernandes


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2019
Verified
Book Chapter
Open access
PDF file
NFNatasha Fernandes
Natasha Fernandes
MDMark Dras
Mark Dras
AMAnnabelle McIver
Annabelle McIver
We address the problem of how to “obfuscate” texts by removing stylistic clues which can identify authorship, whilst preserving (as much as possible) the content of the text. In this paper we combine ideas from “generalised differential privacy” and machine learning techniques for text processing to model privacy for text documents. We define a privacy mechanism that operates at the level of text documents represented as “bags-of-words”—these representations are typical in machine learning and contain sufficient information to carry out many kinds of classification tasks including topic identification and authorship attribution (of the original documents). We show that our mechanism satisfies privacy with respect to a metric for semantic similarity, thereby providing a balance between utility, defined by the semantic content of texts, with the obfuscation of stylistic clues. We demonstrate our implementation on a “fan fiction” dataset, confirming that it is indeed possible to disguise writing style effectively whilst preserving enough information and variation for accurate content classification tasks. We refer the reader to our complete paper [ 15 ] which contains full proofs and further experimentation details.

1 June 2019
Verified
Conference Paper
Closed access
KCKonstantinos Chatzikokolakis
Konstantinos Chatzikokolakis
NFNatasha Fernandes
Natasha Fernandes
Catuscia PalamidessiCatuscia Palamidessi
Catuscia Palamidessi
Quantitative Information Flow (QIF) and Differential Privacy (DP) are both concerned with the protection of sensitive information, but they are rather different approaches. In particular, QIF considers the expected probability of a successful attack, while DP (in both its standard and local versions) is a max-case measure, in the sense that it is compromised by the existence of a possible attack, regardless of its probability. Comparing systems is a fundamental task in these areas: one wishes to guarantee that replacing a system A by a system B is a safe operation, that is the privacy of B is no-worse than that of A. In QIF, a refinement order provides strong such guarantees, while in DP mechanisms are typically compared (w.r.t. privacy) based on the ε privacy parameter that they provide. In this paper we explore a variety of refinement orders, inspired by the one of QIF, providing precise guarantees for max-case leakage. We study simple structural ways of characterising them, the relation between them, efficient methods for verifying them and their lattice properties. Moreover, we apply these orders in the task of comparing DP mechanisms, raising the question of whether the order based on ε provides strong privacy guarantees. We show that, while it is often the case for mechanisms of the same "family" (geometric, randomised response, etc.), it rarely holds across different families.

3 February 2015 in Journal of Hospital Medicine
Verified
Journal Article
Open access
PDF file
GDGregory S. Day
Gregory S. Day
SLSafiya Ladak
Safiya Ladak
KCKevin Curley
Kevin Curley
NFNorman Farb
Norman Farb
PMPaul Masiowski
Paul Masiowski
CCC Martin del Campo
C Martin del Campo
BACKGROUND: Patients with suspected thiamine deficiency should receive treatment with parenteral thiamine to achieve the high serum thiamine levels necessary to reverse the effects of deficiency and to circumvent problems with absorption common in the medically ill.OBJECTIVE: To quantify rates of parenteral administration of thiamine across university‐affiliated hospitals and to identify factors associated with higher rates of parenteral prescribing.DESIGN: Multicenter, retrospective observational study of thiamine prescriptions.METHODS: Prescriptions for thiamine were captured from computerized pharmacy information systems across participating centers, providing information concerning dose, route, frequency, and duration of thiamine prescribed from January 2010 to December 2011.SETTING: Fourteen university‐affiliated tertiary care hospitals geographically distributed across Canada, including 48,806 prescriptions for thiamine provided to 32,213 hospitalized patients.RESULTS: Parenteral thiamine accounted for a statistically significant majority of thiamine prescriptions (57.6%, P < 0.001); however, oral thiamine constituted a significant majority of the total doses prescribed (68.4%, z = 168.9; P < 0.001). Protocols prioritizing parenteral administration were associated with higher rates of parenteral prescribing (61.3% with protocol, 45.8% without protocol; P < 0.001). Patients admitted under psychiatry services were significantly more likely to be prescribed oral thiamine (P < 0.001).CONCLUSIONS: Although parenteral thiamine accounted for a statistically significant majority of prescriptions, oral thiamine was commonly prescribed within academic hospitals. Additional strategies are needed to promote parenteral thiamine prescribing to patients with suspected thiamine deficiency. Journal of Hospital Medicine 2015;10:246–253. © 2015 Society of Hospital Medicine

2 October 2021
Verified
Book Chapter
Closed access
PDF file
NFNatasha Fernandes
Natasha Fernandes
YKYusuke Kawamoto
Yusuke Kawamoto
TMTakao Murakami
Takao Murakami

12 July 2018
Verified
Book Chapter
Closed access
PDF file
NFNatasha Fernandes
Natasha Fernandes
MDMark Dras
Mark Dras
AMAnnabelle McIver
Annabelle McIver

15 November 2023
Verified
Conference Paper
Open access
MAMário Alvim
Mário Alvim
NFNatasha Fernandes
Natasha Fernandes
AMAnnabelle McIver
Annabelle McIver
CMCarroll Morgan
Carroll Morgan
GNGabriel H. Nunes
Gabriel H. Nunes
We combine Kronecker products, and quantitative information flow, to give a novel formal analysis for the fine-grained verification of utility in complex privacy pipelines. The combination explains a surprising anomaly in the behaviour of utility of privacy-preserving pipelines - that sometimes a reduction in privacy results also in a decrease in utility. We use the standard measure of utility for Bayesian analysis, introduced by Ghosh at al. [1], to produce tractable and rigorous proofs of the fine-grained statistical behaviour leading to the anomaly. More generally, we offer the prospect of formal-analysis tools for utility that complement extant formal analyses of privacy. We demonstrate our results on a number of common privacy-preserving designs.