Advances in imaging technologies, combined with inexpensive storage, have led to an explosion in the volume of publicly available neuroimaging datasets. Effective analyses of these images hold the potential for uncovering mechanisms that govern functioning of the human brain, and understanding various neurological diseases and disorders. The potential significance of these studies notwithstanding, a growing concern relates to the protection of privacy and confidentiality of subjects who participate in these studies. In this paper, we present a de-anonymization attack rooted in the innate uniqueness of the structure and function of the human brain. We show that the attack reveals not only the identity of an individual, but also the task they are performing, and their efficacy in performing the tasks. Our attack relies on novel matrix analyses techniques that are used to extract discriminating features in neuroimages. These features correspond to individual-specific signatures that can be matched across datasets to yield highly accurate identification. We present data preprocessing, signature extraction, and matching techniques that are computationally inexpensive, and can scale to large datasets. We discuss implications of the attack and challenges associated with defending against such attacks.
Releasing connection data from social networking services can pose a significant threat to user privacy. In our work, we consider structural social network de-anonymization attacks, which are used when a malicious party uses connections in a public or other identified network to re-identify users in an anonymized social network release that he obtained previously. In this paper we design and evaluate a novel social de-anonymization attack. In particular, we argue that the similarity function used to re-identify nodes is a key component of such attacks, and we design a novel measure tailored fo…
Data sharing between different organizations is an essential process in today's connected world. However, recently there were many concerns about data sharing as sharing sensitive information can jeopardize users' privacy. To preserve the privacy, organizations use anonymization techniques to conceal users' sensitive data. However, these techniques are vulnerable to de-anonymization attacks which aim to identify individual records within a dataset. In this paper, a two-tier mathematical framework is proposed for analyzing and mitigating the de-anonymization attacks, by studying the interaction…
There are a number of vectors for attack when trying to link an individual to a certain DNA sequence. Phenotypic prediction is one such vector; linking DNA to an individual based on their traits. Current approaches are not overly effective, due to a number of real world considerations. This report will improve upon current phenotypic prediction, and suggest a number of methods for defending against such an attack.
L3S Research Center, Leibniz University（莱布尼茨大学L3S研究中心）；University of Applied Sciences Osnabrück（奥斯纳布吕克应用科学大学）；University of Applied Sciences and Arts Hannover（汉诺威应用科学与艺术大学）
Mining health data can lead to faster medical decisions, improvement in the quality of treatment, disease prevention, reduced cost, and it drives innovative solutions within the healthcare sector. However, health data is highly sensitive and subject to regulations such as the General Data Protection Regulation (GDPR), which aims to ensure patient's privacy. Anonymization or removal of patient identifiable information, though the most conventional way, is the first important step to adhere to the regulations and incorporate privacy concerns. In this paper, we review the existing anonymization t…
For a better understanding of anonymization methods for location traces, we have designed and held a location trace anonymization contest that deals with a long trace (400 events per user) and fine-grained locations (1024 regions). In our contest, each team anonymizes her original traces, and then the other teams perform privacy attacks against the anonymized traces. In other words, both defense and attack compete together, which is close to what happens in real life. Prior to our contest, we show that re-identification alone is insufficient as a privacy risk and that trace inference should be…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；Mark and Mary Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California（南加州大学凯克医学院马克与玛丽·史蒂文斯神经影像与信息学研究所）；University of Southern California（南加州大学）
Ensuring the privacy of research participants is vital, even more so in healthcare environments. Deep learning approaches to neuroimaging require large datasets, and this often necessitates sharing data between multiple sites, which is antithetical to the privacy objectives. Federated learning is a commonly proposed solution to this problem. It circumvents the need for data sharing by sharing parameters during the training process. However, we demonstrate that allowing access to parameters may leak private information even if data is never directly shared. In particular, we show that it is pos…
Privacy is of the utmost concern when it comes to releasing data to third parties. Data owners rely on anonymization approaches to safeguard the released datasets against re-identification attacks. However, even with strict anonymization in place, re-identification attacks are still a possibility and in many cases a reality. Prior art has focused on providing better anonymization algorithms with minimal loss of information and how to prevent data disclosure attacks. Our approach tries to tackle the issue of tracing re-identification attacks based on the concept of honeytokens, decoy or "bait" …
Vast amounts of information of all types are collected daily about people by governments, corporations and individuals. The information is collected when users register to or use on-line applications, receive health related services, use their mobile phones, utilize search engines, or perform common daily activities. As a result, there is an enormous quantity of privately-owned records that describe individuals' finances, interests, activities, and demographics. These records often include sensitive data and may violate the privacy of the users if published. The common approach to safeguarding…
Anonymized data is highly valuable to both businesses and researchers. A large body of research has however shown the strong limits of the de-identification release-and-forget model, where data is anonymized and shared. This has led to the development of privacy-preserving query-based systems. Based on the idea of "sticky noise", Diffix has been recently proposed as a novel query-based mechanism satisfying alone the EU Article~29 Working Party's definition of anonymization. According to its authors, Diffix adds less noise to answers than solutions based on differential privacy while allowing f…
We present a new class of statistical de-anonymization attacks against high-dimensional micro-data, such as individual preferences, recommendations, transaction records and so on. Our techniques are robust to perturbation in the data and tolerate some mistakes in the adversary's background knowledge. We apply our de-anonymization methodology to the Netflix Prize dataset, which contains anonymous movie ratings of 500,000 subscribers of Netflix, the world's largest online movie rental service. We demonstrate that an adversary who knows only a little bit about an individual subscriber can easily …
Federated learning (FL) enables distributed computation of machine learning models over various disparate, remote data sources, without requiring to transfer any individual data to a centralized location. This results in an improved generalizability of models and efficient scaling of computation as more sources and larger datasets are added to the federation. Nevertheless, recent membership attacks show that private or sensitive personal data can sometimes be leaked or inferred when model parameters or summary statistics are shared with a central site, requiring improved security solutions. In…
