51 citations · 348 across the 61 of their papers we have counts for
9 papers · 1 filter
Not fit for Purpose: A critical analysis of the 'Five Safes'
Chris Culnane, Benjamin I. P. Rubinstein, David Watts
Adopted by government agencies in Australia, New Zealand and the UK as policy instrument or as embodied into legislation, the 'Five Safes' framework aims to manage risks of releasi…
A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning
Chang Xu, Jun Wang, Yuqing Tang +3
As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutiny. Most recently, NMT systems have been found vuln…
DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees
R. Malinga Perera, Bastian Oetomo, Benjamin I. P. Rubinstein +1
Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures. Despite significan…
A Graph Symmetrisation Bound on Channel Information Leakage under Blowfish Privacy
Tobias Edwards, Benjamin I. P. Rubinstein, Zuhe Zhang +1
Blowfish privacy is a recent generalisation of differential privacy that enables improved utility while maintaining privacy policies with semantic guarantees, a factor that has dri…
Discrete Few-Shot Learning for Pan Privacy
Roei Gelbhart, Benjamin I. P. Rubinstein
In this paper we present the first baseline results for the task of few-shot learning of discrete embedding vectors for image recognition. Few-shot learning is a highly researched…
Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors
Ruihan Zhang, Prashan Madumal, Tim Miller +2
Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. This deficiency remains a key challenge when applying C…
Needle in a Haystack: Label-Efficient Evaluation under Extreme Class Imbalance
Neil G. Marchant, Benjamin I. P. Rubinstein
Important tasks like record linkage and extreme classification demonstrate extreme class imbalance, with 1 minority instance to every 1 million or more majority instances. Obtainin…
Assessing Centrality Without Knowing Connections
Leyla Roohi, Benjamin I. P. Rubinstein, Vanessa Teague
We consider the privacy-preserving computation of node influence in distributed social networks, as measured by egocentric betweenness centrality (EBC). Motivated by modern communi…
Legion: Best-First Concolic Testing
Dongge Liu, Gidon Ernst, Toby Murray +1
Concolic execution and fuzzing are two complementary coverage-based testing techniques. How to achieve the best of both remains an open challenge. To address this research problem,…