Measuring Re-identification Risk

04/12/2023
by   CJ Carey, et al.
0

Compact user representations (such as embeddings) form the backbone of personalization services. In this work, we present a new theoretical framework to measure re-identification risk in such user representations. Our framework, based on hypothesis testing, formally bounds the probability that an attacker may be able to obtain the identity of a user from their representation. As an application, we show how our framework is general enough to model important real-world applications such as the Chrome's Topics API for interest-based advertising. We complement our theoretical bounds by showing provably good attack algorithms for re-identification that we use to estimate the re-identification risk in the Topics API. We believe this work provides a rigorous and interpretable notion of re-identification risk and a framework to measure it that can be used to inform real-world applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/08/2023

On the Robustness of Topics API to a Re-Identification Attack

Web tracking through third-party cookies is considered a threat to users...
research
06/06/2023

Interest-disclosing Mechanisms for Advertising are Privacy-Exposing (not Preserving)

Today, targeted online advertising relies on unique identifiers assigned...
research
05/01/2020

Improving Robustness via Risk Averse Distributional Reinforcement Learning

One major obstacle that precludes the success of reinforcement learning ...
research
06/11/2023

RestGPT: Connecting Large Language Models with Real-World Applications via RESTful APIs

Tool-augmented large language models (LLMs) have achieved remarkable pro...
research
03/31/2022

Assessing the risk of re-identification arising from an attack on anonymised data

Objective: The use of routinely-acquired medical data for research purpo...
research
05/05/2023

Judge Me in Context: A Telematics-Based Driving Risk Prediction Framework in Presence of Weak Risk Labels

Driving risk prediction has been a topic of much research over the past ...
research
01/21/2013

A formalization of re-identification in terms of compatible probabilities

Re-identification algorithms are used in data privacy to measure disclos...

Please sign up or login with your details

Forgot password? Click here to reset