Anonymous Tool Research Articles

Artificial intelligence in pediatric echocardiography-Automated view classification and image anonymization in rare cardiac malformations on the example of borderline HLHS

Abstract Background/Introduction Artificial intelligence (AI) has already much potential in adult echocardiography. However, there is still few experience in how to effectively implement AI methods in pediatric echocardiography. Since children with congenital heart defects show a large anatomical variance, AI-based image analysis tools adapted to this group are necessary. For the fundamentally needed steps of an automatic image data anonymization and a view classification there are still no reliable tools available. Purpose We have developed an anonymization tool for pediatric echocardiography data. For effective automated analysis of echocardiographies in children, we established an algorithm using bHLHS as an example that requires only small numbers of patients for a good view classification accuracy. Thus, we expect that the algorithm will also be applicable to other cardiac malformations. Method Raw data were obtained from visage imaging platforms and echocardiography examinations were conducted on Siemens machines. An anonymization tool was developed using the Python programming language and the Tkinter library. It converts medical images and crops the embedded data from the non-anatomical top region. The classification neural network was evaluated with data obtained from 5 patients with bHLHS. After data cleaning, each patient's image is labelled according to different Echo views: 4CH, SA, and LA, creating a total of 6600 images of 3 separate views. Due to the limited echocardiography dataset, a data augmentation approach was employed to improve the generalization of the AI model. The transfer learning approach was used to develop the AI model, which utilized a pre-trained VGG 13 model that was modified to classify the three different views of the pediatric echocardiography dataset. The modified model was fine-tuned on the dataset with a GPU-enhanced Intel i9 platform and Pycharm 2022.2.4. We use 70% dataset for training, 20% dataset for testing, and 10% dataset for validating. Results Table 1 shows that the expert clinician validated the anonymization tool by comparing identified patient information in the raw image and anonymized image. The trained pediatric echocardiography view classification model achieved an overall accuracy of 0.776 with precision values of 0.725, 0.889, and 0.775 for LA, SA and 4CH classes, respectively. The F1 score values were 0.835, 0.690, and 0.778 for the same classes. ROC curve were plotted (Figure 1) to visualize the performance of the model. Conclusion This study shows the importance of data anonymization and view classification in automating the diagnosis of HLHS using echocardiography images. The developed deep learning algorithm showed promising performance in accurately classifying different views of echocardiography images for diagnosing HLHS. Future studies can build upon this work by developing a complete diagnostic system to automatically analyze cardiac structures of patients with cardiac malformations.

A Self-adaptive and Secure Approach to Share Network Trace Data

A large volume of network trace data are collected by the government and public and private organizations and can be analyzed for various purposes such as resolving network problems, improving network performance, and understanding user behavior. However, most organizations are reluctant to share their data with any external experts for analysis, because they contain sensitive information deemed proprietary to the organization, thus raising privacy concerns. Even if the payload of network packets is not shared, header data may disclose sensitive information that adversaries can exploit to perform unauthorized actions. So network trace data need to be anonymized before being shared. Most of the existing anonymization tools have two major shortcomings: (1) they cannot provide provable protection, and (2) their performance relies on setting the right parameter values such as the degree of privacy protection and the features that should be anonymized, but there is little assistance for a user to optimally set these parameters. This article proposes a self-adaptive and secure approach to anonymize network trace data and provides provable protection and automatic optimal settings of parameters. A comparison of the proposed approach with existing anonymization tools via experimentation demonstrated that the proposed method outperforms the existing anonymization techniques.

Collecting, Processing and Secondary Using Personal and (Pseudo)Anonymized Data in Smart Cities

Smart cities, leveraging IoT technologies, are revolutionizing the quality of life for citizens. However, the massive data generated in these cities also poses significant privacy risks, particularly in de-anonymization and re-identification. This survey focuses on the privacy concerns and commonly used techniques for data protection in smart cities, specifically addressing geolocation data and video surveillance. We categorize the attacks into linking, predictive and inference, and side-channel attacks. Furthermore, we examine the most widely employed de-identification and anonymization techniques, highlighting privacy-preserving techniques and anonymization tools; while these methods can reduce the privacy risks, they are not enough to address all the challenges. In addition, we argue that de-identification must involve properties such as unlikability, selective disclosure and self-sovereignty. This paper concludes by outlining future research challenges in achieving complete de-identification in smart cities.

F-ACCUMUL: A Protocol Fingerprint and Accumulative Payload Length Sample-Based Tor-Snowflake Traffic-Identifying Framework

Tor is widely used to protect users’ privacy, which is the most popular anonymous tool. Tor introduces multiple pluggable transports (PT) to help users avoid censorship. A number of traffic analysis methods have been devoted to de-anonymize these PT. Snowflake is the latest PT based on the WebRTC protocol and DTLS encryption protocol for peer-to-peer communication, differing from other PT, which defeat these traffic analysis methods. In this paper, we propose a Snowflake traffic identification framework, which can identify whether the user is accessing Tor and which hidden service he is visiting. Rule matching and DTLS handshake fingerprint features are utilized to classify Snowflake traffic. The linear interpolation of the accumulative payload length of the first n messages in the DTLS data transmission phase as additional features are extracted to identify the hidden service. The experimental results show that our identification framework F-ACCUMUL can effectively identify Tor-Snowflake traffic and Tor-Snowflake hidden service traffic.

Anonymity Technologies in Investigative Journalism: A Tool for Inspiring Trust in Sources

ABSTRACT Investigative journalism, like other sectors of social life, has undergone significant changes due to globalization, technological progress, and the Western world’s turn to neoliberalism. This context has facilitated the emergence of new practices within the profession, particularly new modes of communication between journalists and their confidential sources. This qualitative study focuses on the meaning journalists attribute to the use of these technologies in their relationships with their sources. Anonymity tools are being used to build the professional identity of investigative journalism (both collectively and individually) and therefore constitute a resource in the power relationship between journalists and their sources, a relationship that is not fundamentally changed by their use.

A Chinese multi-modal neuroimaging data release for increasing diversity of human brain mapping

The big-data use is becoming a standard practice in the neuroimaging field through data-sharing initiatives. It is important for the community to realize that such open science effort must protect personal, especially facial information when raw neuroimaging data are shared. An ideal tool for the face anonymization should not disturb subsequent brain tissue extraction and further morphological measurements. Using the high-resolution head images from magnetic resonance imaging (MRI) of 215 healthy Chinese, we discovered and validated a template effect on the face anonymization. Improved facial anonymization was achieved when the Chinese head templates but not the Western templates were applied to obscure the faces of Chinese brain images. This finding has critical implications for international brain imaging data-sharing. To facilitate the further investigation of potential culture-related impacts on and increase diversity of data-sharing for the human brain mapping, we released the 215 Chinese multi-modal MRI data into a database for imaging Chinese young brains, namely’I See your Brains (ISYB)’, to the public via the Science Data Bank (https://doi.org/10.11922/sciencedb.00740).

Data Anonymization for Pervasive Health Care: Systematic Literature Mapping Study.

BackgroundData science offers an unparalleled opportunity to identify new insights into many aspects of human life with recent advances in health care. Using data science in digital health raises significant challenges regarding data privacy, transparency, and trustworthiness. Recent regulations enforce the need for a clear legal basis for collecting, processing, and sharing data, for example, the European Union’s General Data Protection Regulation (2016) and the United Kingdom’s Data Protection Act (2018). For health care providers, legal use of the electronic health record (EHR) is permitted only in clinical care cases. Any other use of the data requires thoughtful considerations of the legal context and direct patient consent. Identifiable personal and sensitive information must be sufficiently anonymized. Raw data are commonly anonymized to be used for research purposes, with risk assessment for reidentification and utility. Although health care organizations have internal policies defined for information governance, there is a significant lack of practical tools and intuitive guidance about the use of data for research and modeling. Off-the-shelf data anonymization tools are developed frequently, but privacy-related functionalities are often incomparable with regard to use in different problem domains. In addition, tools to support measuring the risk of the anonymized data with regard to reidentification against the usefulness of the data exist, but there are question marks over their efficacy.ObjectiveIn this systematic literature mapping study, we aim to alleviate the aforementioned issues by reviewing the landscape of data anonymization for digital health care.MethodsWe used Google Scholar, Web of Science, Elsevier Scopus, and PubMed to retrieve academic studies published in English up to June 2020. Noteworthy gray literature was also used to initialize the search. We focused on review questions covering 5 bottom-up aspects: basic anonymization operations, privacy models, reidentification risk and usability metrics, off-the-shelf anonymization tools, and the lawful basis for EHR data anonymization.ResultsWe identified 239 eligible studies, of which 60 were chosen for general background information; 16 were selected for 7 basic anonymization operations; 104 covered 72 conventional and machine learning–based privacy models; four and 19 papers included seven and 15 metrics, respectively, for measuring the reidentification risk and degree of usability; and 36 explored 20 data anonymization software tools. In addition, we also evaluated the practical feasibility of performing anonymization on EHR data with reference to their usability in medical decision-making. Furthermore, we summarized the lawful basis for delivering guidance on practical EHR data anonymization.ConclusionsThis systematic literature mapping study indicates that anonymization of EHR data is theoretically achievable; yet, it requires more research efforts in practical implementations to balance privacy preservation and usability to ensure more reliable health care applications.

Synthesis of COVID-19 chest X-rays using unpaired image-to-image translation

Motivated by the lack of publicly available datasets of chest radiographs of positive patients with coronavirus disease 2019 (COVID-19), we build the first-of-its-kind open dataset of synthetic COVID-19 chest X-ray images of high fidelity using an unsupervised domain adaptation approach by leveraging class conditioning and adversarial training. Our contributions are twofold. First, we show considerable performance improvements on COVID-19 detection using various deep learning architectures when employing synthetic images as additional training set. Second, we show how our image synthesis method can serve as a data anonymization tool by achieving comparable detection performance when trained only on synthetic data. In addition, the proposed data generation framework offers a viable solution to the COVID-19 detection in particular, and to medical image classification tasks in general. Our publicly available benchmark dataset (https://github.com/hasibzunair/synthetic-covid-cxr-dataset.) consists of 21,295 synthetic COVID-19 chest X-ray images. The insights gleaned from this dataset can be used for preventive actions in the fight against the COVID-19 pandemic.

ОСОБЕННОСТИ КОГНИТИВНОЙ ФЛЕКСИБИЛЬНОСТИ УЧАСТНИКОВ РЫНКА ТРУДА Г. НОВОСИБИРСКА

The level of a person’s activity in the labour market mainly depends on the development of cognitive flexibility – mental ability characterizing the skill of an individual to transform cognitive attitudes adapting to new requirements of the present. The paper presents the results of measuring the cognitive flexibility of labour market members (on a sample of 380 professionally active residents of Novosibirsk). The authors measured cognitive flexibility using the Dennis & Vander Wal Cognitive Flexibility Inventory (CFI) questionnaire adapted for the Kurginyan & Osavolyuk Russian-speaking sample. The respondents were interviewed using the Google Forms anonymous survey tool. The paper aims at the study of special aspects of cognitive flexibility of Novosibirsk labour market participants. The authors studied the relations between the personal data of labour market participants (gender, age, education, marital status, financial situation, degree of activity in professional self-development) and cognitive flexibility (integral indicator and Alternatives and Control scales. The study identified that the respondents of the senior generation had a higher degree of activity in professional self-development and family people had the lower one. The Cognitive Flexibility integral indicator is most positively associated with the level of material well-being of the respondents, their involvement in the professional self-development. The authors mention gender dependence of the respondents’ cognitive flexibility indicators: the integral cognitive flexibility indicator and the Alternative scale indicator are higher in women, and the Control scale indicator is higher in men.

Identifying the values associated with users’ behavior towards anonymity tools through means-end analysis

Concerns about privacy and frustration over censorship and content blocking urge a great number of users to use privacy enhancing products. This research focuses on anonymity tools, as a Privacy Enhancing Technology (PET), investigating the human values associated with users’ behavior towards them. We use means-end analysis, a methodology we consider to be appropriate for investigating users’ conceptions and incentives that determine acceptance and use of anonymity tools. In this context we use the laddering technique, a qualitative method based on in-depth interviews, to identify the chains of attribute-consequence-value of anonymity tools users and to construct a Hierarchical Value Map. The results show that freedom, personal privacy, economic prosperity, professional development and fear-free living are the core values users achieve as a result of anonymity tools use. The aim of our research is to provide insights and enhance understanding of anonymity tools users’ behavior, which we expect to benefit both researchers and software engineers to design more effective tools.

X 2 R 2

Reidentification-risk analysis and anonymity have received a great deal of attention in the last two decades. While the research community has been developing several privacy notions and the algorithms to achieve them, these tools have faced difficulties in being transferred to the wider audience of practitioners, for they require a considerable amount of data privacy technical knowledge. We demonstrate X 2 R 2 (Explainable Explorative Reidentification Risk), a data anonymization tool for the laymen. X 2 R 2 guides the user through a transparent explorative process, during which the existing reidentification risks are explained and quantified, possible data transformation options are recommended, and the consequences of these operations, in terms of privacy risk and data utility, are clearly shown.

A Big Data-Enabled Hierarchical Framework for Traffic Classification

According to the critical requirements of the Internet, a wide range of privacy-preserving technologies are available, e.g. proxy sites, virtual private networks, and anonymity tools. Such mechanisms are challenged by traffic-classification endeavors which are crucial for network-management tasks and have recently become a milestone in their privacy-degree assessment, both from attacker and designer standpoints. Further, the new Internet era is characterized by the capillary distribution of smart devices leveraging high-capacity communication infrastructures: this results in huge amount of heterogeneous network traffic, i.e. big data. Hence, herein we present BDeH, a novel hierarchical framework for traffic classification of anonymity tools. BDeH is enabled by big data-paradigm and capitalizes the machine learning workhorse for operating with encrypted traffic. In detail, our proposal allows for seamless integration of data parallelism provided by big-data technologies with model parallelism enabled by hierarchical approaches. Results prove that the so-achieved double parallelism carries no negative impact on traffic-classification effectiveness at any granularity level and achieves non negligible performance enhancements with respect to non-hierarchical architectures ( $+4.5\%$ F-measure). Also, it significantly gains over either pure data or pure model parallelism (resp. centralized) approaches by reducing both training completion time—up to $78\%$ (resp. $90\%$ )—and cloud-deployment cost—up to $31\%$ (resp. $10\%$ ).

The impact of an audience response system on a summative assessment, a controlled field study

BackgroundAudience response systems allow to activate the audience and to receive a direct feedback of participants during lectures. Modern systems do not require any proprietary hardware anymore. Students can directly respond on their smartphone. Several studies reported about a high level of satisfaction of students when audience response systems are used, however their impact on learning success is still unclear.MethodsIn order to evaluate the impact of an audience response system on the learning success we implemented the audience response system eduVote into a seminar series and performed a controlled crossover study on its impact on assessments. One hundred fifty-four students in nine groups were taught the same content. In four groups, eduVote was integrated for the first topic while five groups were taught this topic without the audience response systems. For a second topic, the groups were switched: Those groups who were taught before using eduVote were now taught without the audience response system and vice versa. We then analysed the impact of the audience response system on the students’ performance in a summative assessment and specifically focused on questions dealing with the topic, for which the audience response system was used during teaching. We further assessed the students’ perception on the use of eduVote using questionnaires.ResultsIn our controlled crossover study we could not confirm an impact of the audience response system eduVote on long-term persistence i.e. the students’ performance in the summative assessment. Our evaluation revealed that students assessed the use of eduVote very positively, felt stronger engaged and better motivated to deal with the respective topics and would prefer their integration into additional courses as well. In particular we identified that students who feel uncomfortable with answering questions in front of others profit from the use of an audience response system during teaching.ConclusionsAudience response systems motivate and activate students and increase their engagement during classes. However, their impact on long-term persistence and summative assessments may be limited. Audience response systems, however, specifically allow activating students which cannot be reached by the traditional way of asking questions without such an anonymous tool.

A Dive into the Dark Web: Hierarchical Traffic Classification of Anonymity Tools

Privacy-preserving protocols and tools are increasingly adopted by Internet users nowadays. These mechanisms are challenged by the process of traffic classification (TC) which, other than being an important workhorse for several network management tasks, becomes a key factor in the assessment of their privacy level, both from offensive (malign) and defensive (benign) standpoints. In this paper, we propose TC of anonymity tools (and deeper, of their running services and applications) via a truly hierarchical approach . Capitalizing a public dataset released in 2017 containing anonymity traffic, we provide an in-depth analysis of TC and we compare the proposed hierarchical approach with a flat counterpart. The proposed framework is investigated in both the usual TC setup and its “early” variant (i.e., only the first segments of traffic aggregate are used to take a decision). Results highlight a general improvement over the flat approach in terms of all the classification metrics. Further performance gains are also accomplished by tuning the thresholds ensuring progressive censoring. Finally, fine-grain performance investigation allows us to demonstrate lower severity of errors incurred by the hierarchical approach (as opposed to the flat case) and highlight poorly classifiable services/applications of each anonymity tool, gathering useful feedback on their privacy level.

Anonymity Services Tor, I2P, JonDonym: Classifying in the Dark (Web)

Traffic Classification (TC) is an important tool for several tasks, applied in different fields (security, management, traffic engineering, R&D). This process is impaired or prevented by privacy-preserving protocols and tools, that encrypt the communication content, and (in case of anonymity tools) additionally hide the source, the destination, and the nature of the communication. In this paper, leveraging a public dataset released in 2017, we provide classification results with the aim of investigating to which degree the specific anonymity tool (and the traffic it hides) can be identified, when compared to the traffic of other considered anonymity tools, using five machine learning classifiers. Initially, flow-based TC is considered, and the effects of feature importance and temporal-related features to the network are investigated. Additionally, the role of finer-grained features, such as the (joint) histogram of packet lengths (and inter-arrival times), is determined. Successively, “early” TC of anonymous networks is analyzed. Results show that the considered anonymity networks (Tor, I2P, JonDonym) can be easily distinguished (with an accuracy of 99.87% and 99.80%, in case of flow-based and early-TC, respectively), telling even the specific application generating the traffic (with an accuracy of 73.99% and 66.76%, in case of flow-based and early-TC, respectively).

580 Factors Affecting Research Productivity of Burn Surgeons: Results from a Survey of American Burn Association Members

Abstract Introduction While previous studies have examined factors that impact research productivity for surgeons in general, few studies address research productivity specifically of Burn specialists. This study aimed to identify factors that promote and impede research participation and productivity of Burn surgeons, and help elucidate what changes can be made by Departments/Divisions to improve the research productivity. Methods A 44-question anonymous research survey tool was administered to Burn surgeons that are members of the American Burn Association (ABA). The questions analyzed factors such as demographics, career accomplishments, current institution type, educational background, research background, barriers to conducting research, and current research productivity. Chi-square tests were used to analyze significance at p< 0.05. Results Most respondents reported not having any protected research time (71.4%) or resources provided by their institution (84.5%). A majority believed increasing regulatory policies/IRB restrictions have negatively impacted productivity (65.1%). Factors associated with positive impact on research productivity included having a mentor, conducting research prior to completing residency, and provision of research resources from institution such as statistical support, start-up funds, grant writing support, and laboratory space. Age and gender had no statistically impact on research productivity. Conclusions Burn surgeons are more likely to publish research and to receive grants when they have mentors, a history of research prior to completion of residency, and research resources from their institution. Barriers to research productivity include lack of institutional support, lack of protected research time, and increased regulatory policy. Applicability of Research to Practice This study provides a starting point for analyzing factors that contribute to research success amongst burn surgeons. Individually, burn surgeons must take better advantage of the resources available to them through organizations such as the American Burn Association and seek mentorship where available. Surgical departments should aim to increase research resources for burn surgeons, honor protected research time, and strive to create a culture of research activity if research productivity is the goal.

Flexible data anonymization using ARX—Current status and challenges ahead

SummaryThe race for innovation has turned into a race for data. Rapid developments of new technologies, especially in the field of artificial intelligence, are accompanied by new ways of accessing, integrating, and analyzing sensitive personal data. Examples include financial transactions, social network activities, location traces, and medical records. As a consequence, adequate and careful privacy management has become a significant challenge. New data protection regulations, for example in the EU and China, are direct responses to these developments. Data anonymization is an important building block of data protection concepts, as it allows to reduce privacy risks by altering data. The development of anonymization tools involves significant challenges, however. For instance, the effectiveness of different anonymization techniques depends on context, and thus tools need to support a large set of methods to ensure that the usefulness of data is not overly affected by risk‐reducing transformations. In spite of these requirements, existing solutions typically only support a small set of methods. In this work, we describe how we have extended an open source data anonymization tool to support almost arbitrary combinations of a wide range of techniques in a scalable manner. We then review the spectrum of methods supported and discuss their compatibility within the novel framework. The results of an extensive experimental comparison show that our approach outperforms related solutions in terms of scalability and output data quality—while supporting a much broader range of techniques. Finally, we discuss practical experiences with ARX and present remaining issues and challenges ahead.

A comprehensive tool for creating and evaluating privacy-preserving biomedical prediction models

BackgroundModern data driven medical research promises to provide new insights into the development and course of disease and to enable novel methods of clinical decision support. To realize this, machine learning models can be trained to make predictions from clinical, paraclinical and biomolecular data. In this process, privacy protection and regulatory requirements need careful consideration, as the resulting models may leak sensitive personal information. To counter this threat, a wide range of methods for integrating machine learning with formal methods of privacy protection have been proposed. However, there is a significant lack of practical tools to create and evaluate such privacy-preserving models. In this software article, we report on our ongoing efforts to bridge this gap.ResultsWe have extended the well-known ARX anonymization tool for biomedical data with machine learning techniques to support the creation of privacy-preserving prediction models. Our methods are particularly well suited for applications in biomedicine, as they preserve the truthfulness of data (e.g. no noise is added) and they are intuitive and relatively easy to explain to non-experts. Moreover, our implementation is highly versatile, as it supports binomial and multinomial target variables, different types of prediction models and a wide range of privacy protection techniques. All methods have been integrated into a sound framework that supports the creation, evaluation and refinement of models through intuitive graphical user interfaces. To demonstrate the broad applicability of our solution, we present three case studies in which we created and evaluated different types of privacy-preserving prediction models for breast cancer diagnosis, diagnosis of acute inflammation of the urinary system and prediction of the contraceptive method used by women. In this process, we also used a wide range of different privacy models (k-anonymity, differential privacy and a game-theoretic approach) as well as different data transformation techniques.ConclusionsWith the tool presented in this article, accurate prediction models can be created that preserve the privacy of individuals represented in the training set in a variety of threat scenarios. Our implementation is available as open source software.

µ -ANT: semantic microaggregation-based anonymization tool.

Detailed patient data are crucial for medical research. Yet, these healthcare data can only be released for secondary use if they have undergone anonymization. We present and describe µ-ANT, a practical and easily configurable anonymization tool for (healthcare) data. It implements several state-of-the-art methods to offer robust privacy guarantees and preserve the utility of the anonymized data as much as possible. µ-ANT also supports the heterogenous attribute types commonly found in electronic healthcare records and targets both practitioners and software developers interested in data anonymization. (source code, documentation, executable, sample datasets and use case examples) https://github.com/CrisesUrv/microaggregation-based_anonymization_tool.

Trends in Alveolar Bone Grafting and the Use of Recombinant Bone Morphogenetic Protein (RhBMP) in the United States

Objectives: To gather information about current practices and assess the opinions, preferences, and clinical knowledge of surgeons who perform alveolar bone grafts. In addition, surgical training differences in correlation to techniques and outcomes are evaluated. Methods: A survey with both multiple choice and narrative answers regarding surgeons’ practices for alveolar bone grafting was designed and sent via email to members of the American Cleft Palate/Craniofacial Association (ACPA) identified as general craniofacial or oral maxillofacial surgeons. Responses were collected via an anonymous online survey tool. Participants: Members (336) of ACPA identified as craniofacial or oral-maxillofacial surgeons were contacted, and 62 responses were recorded. Results: The majority of survey respondents were oral-maxillofacial surgeons in practice for more than 15 years. 98.4% of respondents had used iliac crest and at least one additional source for grafting, while only 52.7% had performed grafting using recombinant bone morphogenetic protein (RhBMP). 82% used cone beam CT as their evaluation of choice for graft assessment and the majority (62.9%) waited more than 8 weeks postoperatively to image. Chi-square analysis demonstrated significantly longer time in practice for practitioners without craniofacial fellowship training. Conclusions: The results of this study demonstrate that there remains significant variation in alveolar bone grafting practices among surgeons. While some consensus exists, new innovations and technologies will require continued evaluation of surgical practices and outcomes. Long-term follow-up studies are needed especially with regard to the use of RhBMP in alveolar clefts.