Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAuthor Obfuscation Using Generalised Differential Privacy
77
0
0.0
(
0
)
Added by
Natasha Fernandes
Publication date
2018
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
The problem of obfuscating the authorship of a text document has received little attention in the literature to date. Current approaches are ad-hoc and rely on assumptions about an adversarys auxiliary knowledge which makes it difficult to reason about the privacy properties of these methods. Differential privacy is a well-known and robust privacy approach, but its reliance on the notion of adjacency between datasets has prevented its application to text document privacy. However, generalised differential privacy permits the application of differential privacy to arbitrary datasets endowed with a metric and has been demonstrated on problems involving the release of individual data points. In this paper we show how to apply generalised differential privacy to author obfuscation by utilising existing tools and methods from the stylometry and natural language processing literature.
rate research
Read More
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.
As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and serving tasks in the cloud, it is important to protect the privacy of sensitive samples in the training dataset and prevent information leakage to untrusted third parties. Past work have shown that a malicious machine learning service provider or end user can easily extract critical information about the training samples, from the model parameters or even just model outputs. In this paper, we propose a novel and generic methodology to preserve the privacy of training data in machine learning applications. Specifically we introduce an obfuscate function and apply it to the training data before feeding them to the model training task. This function adds random noise to existing samples, or augments the dataset with new samples. By doing so sensitive information about the properties of individual samples, or statistical properties of a group of samples, is hidden. Meanwhile the model trained from the obfuscated dataset can still achieve high accuracy. With this approach, the customers can safely disclose the data or models to third-party providers or end users without the need to worry about data privacy. Our experiments show that this approach can effective defeat four existing types of machine learning privacy attacks at negligible accuracy cost.
The massive collection of personal data by personalization systems has rendered the preservation of privacy of individuals more and more difficult. Most of the proposed approaches to preserve privacy in personalization systems usually address this issue uniformly across users, thus ignoring the fact that users have different privacy attitudes and expectations (even among their own personal data). In this paper, we propose to account for this non-uniformity of privacy expectations by introducing the concept of heterogeneous differential privacy. This notion captures both the variation of privacy expectations among users as well as across different pieces of information related to the same user. We also describe an explicit mechanism achieving heterogeneous differential privacy, which is a modification of the Laplacian mechanism by Dwork, McSherry, Nissim, and Smith. In a nutshell, this mechanism achieves heterogeneous differential privacy by manipulating the sensitivity of the function using a linear transformation on the input domain. Finally, we evaluate on real datasets the impact of the proposed mechanism with respect to a semantic clustering task. The results of our experiments demonstrate that heterogeneous differential privacy can account for different privacy attitudes while sustaining a good level of utility as measured by the recall for the semantic clustering task.
Many data applications have certain invariant constraints due to practical needs. Data curators who employ differential privacy need to respect such constraints on the sanitized data product as a primary utility requirement. Invariants challenge the formulation, implementation, and interpretation of privacy guarantees. We propose subspace differential privacy, to honestly characterize the dependence of the sanitized output on confidential aspects of the data. We discuss two design frameworks that convert well-known differentially private mechanisms, such as the Gaussian and the Laplace mechanisms, to subspace differentially private ones that respect the invariants specified by the curator. For linear queries, we discuss the design of near-optimal mechanisms that minimize the mean squared error. Subspace differentially private mechanisms rid the need for post-processing due to invariants, preserve transparency and statistical intelligibility of the output, and can be suitable for distributed implementation. We showcase the proposed mechanisms on the 2020 Census Disclosure Avoidance demonstration data, and a spatio-temporal dataset of mobile access point connections on a large university campus.
An obfuscator is an algorithm that translates circuits into functionally-equivalent similarly-sized circuits that are hard to understand. Efficient obfuscators would have many applications in cryptography. Until recently, theoretical progress has mainly been limited to no-go results. Recent works have proposed the first efficient obfuscation algorithms for classical logic circuits, based on a notion of indistinguishability against polynomial-time adversaries. In this work, we propose a new notion of obfuscation, which we call partial-indistinguishability. This notion is based on computationally universal groups with efficiently computable normal forms, and appears to be incomparable with existing definitions. We describe universal gate sets for both classical and quantum computation, in which our definition of obfuscation can be met by polynomial-time algorithms. We also discuss some potential applications to testing quantum computers. We stress that the cryptographic security of these obfuscators, especially when composed with translation from other gate sets, remains an open question.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
