Data Mining Practical Machine Learning Tools and Techniques

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

Distance-Regular Graphs

The growing popularity of location-based systems, allowing unknown/untrusted servers to easily collect huge amounts of information regarding users' location, has recently started raising serious privacy concerns. In this paper we introduce geoind, a formal notion of privacy for location-based systems that protects the user's exact location, while allowing approximate information -- typically needed to obtain a certain desired service -- to be released.This privacy definition formalizes the intuitive notion of protecting the user's location within a radius $r$ with a level of privacy that depends on r, and corresponds to a generalized version of the well-known concept of differential privacy. Furthermore, we present a mechanism for achieving geoind by adding controlled random noise to the user's location.We describe how to use our mechanism to enhance LBS applications with geo-indistinguishability guarantees without compromising the quality of the application results. Finally, we compare state-of-the-art mechanisms from the literature with ours. It turns out that, among all mechanisms independent of the prior, our mechanism offers the best privacy guarantees.

Geo-indistinguishability: differential privacy for location-based systems

It is a well-known fact that the progress of personal communication devices leads to serious concerns about privacy in general, and location privacy in particular. As a response to these issues, a number of Location-Privacy Protection Mechanisms (LPPMs) have been proposed during the last decade. However, their assessment and comparison remains problematic because of the absence of a systematic method to quantify them. In particular, the assumptions about the attacker's model tend to be incomplete, with the risk of a possibly wrong estimation of the users' location privacy. In this paper, we address these issues by providing a formal framework for the analysis of LPPMs, it captures, in particular, the prior information that might be available to the attacker, and various attacks that he can perform. The privacy of users and the success of the adversary in his location-inference attacks are two sides of the same coin. We revise location privacy by giving a simple, yet comprehensive, model to formulate all types of location-information disclosure attacks. Thus, by formalizing the adversary's performance, we propose and justify the right metric to quantify location privacy. We clarify the difference between three aspects of the adversary's inference attacks, namely their accuracy, certainty, and correctness. We show that correctness determines the privacy of users. In other words, the expected estimation error of the adversary is the metric of users' location privacy. We rely on well-established statistical methods to formalize and implement the attacks in a tool: the Location-Privacy Meter that measures the location privacy of mobile users, given various LPPMs. In addition to evaluating some example LPPMs, by using our tool, we assess the appropriateness of some popular metrics for location privacy: entropy and k-anonymity. The results show a lack of satisfactory correlation between these two metrics and the success of the adversary in inferring the users' actual locations.

/pdf/quantifying-location-privacy-2v31ih0lts.pdf

Quantifying Location Privacy

Differential Privacy is one of the most prominent frameworks used to deal with disclosure prevention in statistical databases. It provides a formal privacy guarantee, ensuring that sensitive information relative to individuals cannot be easily inferred by disclosing answers to aggregate queries. If two databases are adjacent, i.e. differ only for an individual, then the query should not allow to tell them apart by more than a certain factor. This induces a bound also on the distinguishability of two generic databases, which is determined by their distance on the Hamming graph of the adjacency relation.

/pdf/broadening-the-scope-of-differential-privacy-using-metrics-11ip9ema9w.pdf

Broadening the Scope of Differential Privacy Using Metrics

This paper introduces g-leakage, a rich generalization of the min-entropy model of quantitative information flow. In g-leakage, the benefit that an adversary derives from a certain guess about a secret is specified using a gain function g. Gain functions allow a wide variety of operational scenarios to be modeled, including those where the adversary benefits from guessing a value close to the secret, guessing a part of the secret, guessing a property of the secret, or guessing the secret within some number of tries. We prove important properties of g-leakage, including bounds between min-capacity, g-capacity, and Shannon capacity. We also show a deep connection between a strong leakage ordering on two channels, C1 and C2, and the possibility of factoring C1 into C2C3, for some C3. Based on this connection, we propose a generalization of the Lattice of Information from deterministic to probabilistic channels.

/pdf/measuring-information-leakage-using-generalized-gain-4nile3kt38.pdf

Measuring Information Leakage Using Generalized Gain Functions

We consider the geo-indistinguishability approach to location privacy, and the trade-off with respect to utility. We show that, given a desired degree ofgeo-indistinguishability, it is possible to construct a mechanism that minimizes the service quality loss, using linear programming techniques. In addition we show that, under certain conditions, such mechanism also provides optimal privacy in the sense of Shokri et al. Furthermore, we propose a method to reduce the number of constraints of the linear program from cubic to quadratic, maintaining the privacy guarantees and without affecting significantly the utility of the generated mechanism. This reduces considerably the time required to solve the linear program, thus enlarging significantly the location sets for which the optimal mechanisms can be computed.

Optimal Geo-Indistinguishable Mechanisms for Location Privacy

We consider a framework in which anonymity protocols are interpreted as noisy channels in the information-theoretic sense, and we explore the idea of using the notion of capacity as a measure of the loss of anonymity. Such idea was already suggested by Moskowitz, Newman and Syverson, in their analysis of the covert channel that can be created as a result of non-perfect anonymity. We consider the case in which some leak of information is intended by design, and we introduce the notion of conditional capacity to rule out this factor, thus retrieving a natural correspondence with the notion of anonymity. Furthermore, we show how to compute the capacity and the conditional capacity when the anonymity protocol satisfies certain symmetries. We also investigate how the adversary can test the system to try to infer the user's identity, and we study how his probability of success depends on the characteristics of the channel. We then illustrate how various notions of anonymity can be expressed in this framework, and show the relation with some definitions of probabilistic anonymity in literature. Finally, we show how to compute the matrix of the channel (and hence the capacity and conditional capacity) using model checking.

/pdf/anonymity-protocols-as-noisy-channels-5fgztrxp4u.pdf

Konstantinos Chatzikokolakis

Papers

Geo-indistinguishability: differential privacy for location-based systems

Broadening the Scope of Differential Privacy Using Metrics

Measuring Information Leakage Using Generalized Gain Functions

Optimal Geo-Indistinguishable Mechanisms for Location Privacy

Anonymity protocols as noisy channels