Directional Privacy for Deep Learning

Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. This applies isotropic Gaussian noise to gradients during training, which can perturb these gradients in any direction, damaging utility. Metric DP, however, can provide alternative mechanisms based on arbitrary metrics that might be more suitable. In this paper we apply \textit{directional privacy}, via a mechanism based on the von Mises-Fisher (VMF) distribution, to perturb gradients in terms of \textit{angular distance} so that gradient direction is broadly preserved. We show that this provides $\epsilon d$-privacy for deep learning training, rather than the $(\epsilon, \delta)$-privacy of the Gaussian mechanism; and that experimentally, on key datasets, the VMF mechanism can outperform the Gaussian in the utility-privacy trade-off.

Locality Sensitive Hashing with Extended Differential Privacy

Extended differential privacy, a generalization of standard differential privacy (DP) using a general metric rather than the Hamming metric, has been widely studied to provide rigorous privacy guarantees while keeping high utility. However, existing works on extended DP focus on a specific metric such as the Euclidean metric, the $l_1$ metric, and the Earth Mover's metric, and cannot be applied to other metrics. Consequently, existing extended DP mechanisms are limited to a small number of applications such as location-based services and document processing. In this paper, we propose a mechanism providing extended DP with a wide range of metrics. Our mechanism is based on locality sensitive hashing (LSH) and randomized response, and can be applied to a wide variety of metrics including the angular distance (or cosine) metric, Jaccard metric, Earth Mover's metric, and $l_p$ metric. Moreover, our mechanism works well for personal data in a high-dimensional space. We theoretically analyze the privacy properties of our mechanism, introducing new versions of concentrated and probabilistic extended DP to explain the guarantees provided. Finally, we apply our mechanism to friend matching based on high-dimensional personal data with an angular distance metric in the local model. We show that existing local DP mechanisms such as the RAPPOR do not work in this application. We also show through experiments that our mechanism makes possible friend matching with rigorous privacy guarantees and high utility.

Generalised Differential Privacy for Text Document Processing

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.