Detection of malicious nodes based on consortium blockchain.

With the development of technology, more and more devices are connected to the Internet. According to statistics, Internet of Things (IoT) devices have reached tens of billions of units, which forms a massive Internet of Things system. Social Internet of Things (SIoT) is an essential extension of the IoT system. Because of the heterogeneity present in the SIoT system and the limited resources available, it is facing increasing security issues, which hinders the interaction of SIoT information. Consortium chain combined with the trust problem in SIoT systems has gradually become an important goal to improve the security of SIoT data interaction. Detection of malicious nodes is one of the key points to solve the trust problem. In this article, we focus on the consortium chain network. According to the information characteristics of nodes on the consortium chain, it can be analyzed that the SIoT malicious node detection combined with the consortium chain network should have the privacy protection, subjectivity, uncertainty, lightweight, dynamic timeliness and so on. In response to the features above and the concerns of existing malicious node detection methods, we propose an algorithm based on inter-block delay. We employ unsupervised clustering algorithms, including K-means and DBSCAN, to analyze and compare the data set intercepted from the consortium chain. The results indicate that DBSCAN exhibits the best clustering performance. Finally, we transmit the acquired data onto the chain. We conclude that the proposed algorithm is highly effective in detecting malicious nodes on the combination of SIoT and consortium chain networks.

A simple Cox approach to estimating risk ratios without sharing individual-level data in multi-site studies.

Epidemiologic studies frequently use risk ratios to quantify associations between exposures and binary outcomes. When the data are physically stored at multiple data partners, it can be challenging to perform individual-level analysis if data cannot be pooled centrally due to privacy constraints. Existing methods either require multiple file transfers between each data partner and an analysis center (e.g., distributed regression) or only provide approximate estimation of the risk ratio (e.g., meta-analysis). Here we develop a practical method that requires a single transfer of eight summary-level quantities from each data partner. Our approach leverages an existing risk-set method and software originally developed for Cox regression. Sharing only summary-level information, the proposed method provides risk ratio estimates and confidence intervals identical to those that would be provided - if individual-level data were pooled - by the modified Poisson regression. We justify the method theoretically, confirm its performance using simulated data, and implement it in a distributed analysis of COVID-19 data from the U.S. Food and Drug Administration's Sentinel System.

Machine unlearning in brain-inspired neural network paradigms.

Machine unlearning, which is crucial for data privacy and regulatory compliance, involves the selective removal of specific information from a machine learning model. This study focuses on implementing machine unlearning in Spiking Neuron Models (SNMs) that closely mimic biological neural network behaviors, aiming to enhance both flexibility and ethical compliance of AI models. We introduce a novel hybrid approach for machine unlearning in SNMs, which combines selective synaptic retraining, synaptic pruning, and adaptive neuron thresholding. This methodology is designed to effectively eliminate targeted information while preserving the overall integrity and performance of the neural network. Extensive experiments were conducted on various computer vision datasets to assess the impact of machine unlearning on critical performance metrics such as accuracy, precision, recall, and ROC AUC. Our findings indicate that the hybrid approach not only maintains but in some cases enhances the neural network's performance post-unlearning. The results confirm the practicality and efficiency of our approach, underscoring its applicability in real-world AI systems.

A decentralized federated learning-based cancer survival prediction method with privacy protection.

Background: Survival prediction is one of the crucial goals in precision medicine, as accurate survival assessment can aid physicians in selecting appropriate treatment for individual patients. To achieve this aim, extensive data must be utilized to train the prediction model and prevent overfitting. However, the collection of patient data for disease prediction is challenging due to potential variations in data sources across institutions and concerns regarding privacy and ownership issues in data sharing. To facilitate the integration of cancer data from different institutions without violating privacy laws, we developed a federated learning-based data integration framework called AdFed, which can be used to evaluate patients' survival while considering the privacy protection problem by utilizing the decentralized federated learning technology and regularization method. Results: AdFed was tested on different cancer datasets that contain the patients' information from different institutions. The experimental results show that AdFed using distributed data can achieve better performance in cancer survival prediction (AUC = 0.605) than the compared federated-learning-based methods (average AUC = 0.554). Additionally, to assess the biological interpretability of our method, in the case study we list 10 identified genes related to liver cancer selected by AdFed, among which 5 genes have been proved by literature review. Conclusions: The results indicate that AdFed outperforms better than other federated-learning-based methods, and the interpretable algorithm can select biologically significant genes and pathways while ensuring the confidentiality and integrity of data.

A Web-Based Peer Support Network to Help Care Partners of People With Serious Illness: Co-Design Study.

BACKGROUND: Care partners of people with serious illness experience significant challenges and unmet needs during the patient's treatment period and after their death. Learning from others with shared experiences can be valuable, but opportunities are not consistently available. OBJECTIVE: This study aims to design and prototype a regional, facilitated, and web-based peer support network to help active and bereaved care partners of persons with serious illness be better prepared to cope with the surprises that arise during serious illness and in bereavement. METHODS: An 18-member co-design team included active care partners and those in bereavement, people who had experienced serious illness, regional health care and support partners, and clinicians. It was guided by facilitators and peer network subject-matter experts. We conducted design exercises to identify the functions and specifications of a peer support network. Co-design members independently prioritized network specifications, which were incorporated into an early iteration of the web-based network. RESULTS: The team prioritized two functions: (1) connecting care partners to information and (2) facilitating emotional support. The design process generated 24 potential network specifications to support these functions. The highest priorities included providing a supportive and respectful community; connecting people to trusted resources; reducing barriers to asking for help; and providing frequently asked questions and responses. The network platform had to be simple and intuitive, provide technical support for users, protect member privacy, provide publicly available information and a private discussion forum, and be easily accessible. It was feasible to enroll members in the ConnectShareCare web-based network over a 3-month period. CONCLUSIONS: A co-design process supported the identification of critical features of a peer support network for care partners of people with serious illnesses in a rural setting, as well as initial testing and use. Further testing is underway to assess the long-term viability and impact of the network.

An Extensible Evaluation Framework Applied to Clinical Text Deidentification Natural Language Processing Tools: Multisystem and Multicorpus Study.

BACKGROUND: Clinical natural language processing (NLP) researchers need access to directly comparable evaluation results for applications such as text deidentification across a range of corpus types and the means to easily test new systems or corpora within the same framework. Current systems, reported metrics, and the personally identifiable information (PII) categories evaluated are not easily comparable. OBJECTIVE: This study presents an open-source and extensible end-to-end framework for comparing clinical NLP system performance across corpora even when the annotation categories do not align. METHODS: As a use case for this framework, we use 6 off-the-shelf text deidentification systems (ie, CliniDeID, deid from PhysioNet, MITRE Identity Scrubber Toolkit [MIST], NeuroNER, National Library of Medicine [NLM] Scrubber, and Philter) across 3 standard clinical text corpora for the task (2 of which are publicly available) and 1 private corpus (all in English), with annotation categories that are not directly analogous. The framework is built on shell scripts that can be extended to include new systems, corpora, and performance metrics. We present this open tool, multiple means for aligning PII categories during evaluation, and our initial timing and performance metric findings. Code for running this framework with all settings needed to run all pairs are available via Codeberg and GitHub. RESULTS: From this case study, we found large differences in processing speed between systems. The fastest system (ie, MIST) processed an average of 24.57 (SD 26.23) notes per second, while the slowest (ie, CliniDeID) processed an average of 1.00 notes per second. No system uniformly outperformed the others at identifying PII across corpora and categories. Instead, a rich tapestry of performance trade-offs emerged for PII categories. CliniDeID and Philter prioritize recall over precision (with an average recall 6.9 and 11.2 points higher, respectively, for partially matching spans of text matching any PII category), while the other 4 systems consistently have higher precision (with MIST's precision scoring 20.2 points higher, NLM Scrubber scoring 4.4 points higher, NeuroNER scoring 7.2 points higher, and deid scoring 17.1 points higher). The macroaverage recall across corpora for identifying names, one of the more sensitive PII categories, included deid (48.8%) and MIST (66.9%) at the low end and NeuroNER (84.1%), NLM Scrubber (88.1%), and CliniDeID (95.9%) at the high end. A variety of metrics across categories and corpora are reported with a wider variety (eg, F2-score) available via the tool. CONCLUSIONS: NLP systems in general and deidentification systems and corpora in our use case tend to be evaluated in stand-alone research articles that only include a limited set of comparators. We hold that a single evaluation pipeline across multiple systems and corpora allows for more nuanced comparisons. Our open pipeline should reduce barriers to evaluation and system advancement.

Ethics and responsible AI deployment.

As Artificial Intelligence (AI) becomes more prevalent, protecting personal privacy is a critical ethical issue that must be addressed. This article explores the need for ethical AI systems that safeguard individual privacy while complying with ethical standards. By taking a multidisciplinary approach, the research examines innovative algorithmic techniques such as differential privacy, homomorphic encryption, federated learning, international regulatory frameworks, and ethical guidelines. The study concludes that these algorithms effectively enhance privacy protection while balancing the utility of AI with the need to protect personal data. The article emphasises the importance of a comprehensive approach that combines technological innovation with ethical and regulatory strategies to harness the power of AI in a way that respects and protects individual privacy.

Achieving sustainable medical tourism: unpacking privacy concerns through a tripartite game theoretic lens.

Introduction: Medical tourism has grown significantly, raising critical concerns about the privacy of medical tourists. This study investigates privacy issues in medical tourism from a game theoretic perspective, focusing on how stakeholders' strategies impact privacy protection. Methods: We employed an evolutionary game model to explore the interactions between medical institutions, medical tourists, and government departments. The model identifies stable strategies that stakeholders may adopt to protect the privacy of medical tourists. Results: Two primary stable strategies were identified, with E6(1,0,1) emerging as the optimal strategy. This strategy involves active protection measures by medical institutions, the decision by tourists to forgo accountability, and strict supervision by government departments. The evolution of the system's strategy is significantly influenced by the government's penalty intensity, subsidies, incentives, and the compensatory measures of medical institutions. Discussion: The findings suggest that medical institutions are quick to make decisions favoring privacy protection, while medical tourists tend to follow learning and conformity. Government strategy remains consistent, with increased subsidies and penalties encouraging medical institutions towards proactive privacy protection strategies. We recommend policies to enhance privacy protection in medical tourism, contributing to the industry's sustainable growth.

An n-Dimensional Chaotic Map with Application in Reversible Data Hiding for Medical Images.

The drawbacks of a one-dimensional chaotic map are its straightforward structure, abrupt intervals, and ease of signal prediction. Richer performance and a more complicated structure are required for multidimensional chaotic mapping. To address the shortcomings of current chaotic systems, an n-dimensional cosine-transform-based chaotic system (nD-CTBCS) with a chaotic coupling model is suggested in this study. To create chaotic maps of any desired dimension, nD-CTBCS can take advantage of already-existing 1D chaotic maps as seed chaotic maps. Three two-dimensional chaotic maps are provided as examples to illustrate the impact. The findings of the evaluation and experiments demonstrate that the newly created chaotic maps function better, have broader chaotic intervals, and display hyperchaotic behavior. To further demonstrate the practicability of nD-CTBCS, a reversible data hiding scheme is proposed for the secure communication of medical images. The experimental results show that the proposed method has higher security than the existing methods.

A clustering-based differential privacy protection algorithm for weighted social networks.

Weighted social networks play a crucial role in various fields such as social media analysis, healthcare, and recommendation systems. However, with their widespread application and privacy issues have become increasingly prominent, including concerns related to sensitive information leakage, individual behavior analysis, and privacy attacks. Despite traditional differential privacy protection algorithms being able to protect privacy for edges with sensitive information, directly adding noise to edge weights may result in excessive noise, thereby reducing data utility. To address these challenges, we proposed a privacy protection algorithm for weighted social networks called DCDP. The algorithm combines the density clustering algorithm OPTICS to partition the weighted social network into multiple sub-clusters and adds noise to different sub-clusters at random sampling frequencies. To enhance the balance of privacy protection, we designed a novel privacy parameter calculation method. Through theoretical derivation and experimentation, the DCDP algorithm demonstrated its capability to achieve differential privacy protection for weighted social networks while effectively maintaining data accuracy. Compared to traditional privacy protection algorithms, the DCDP algorithm reduced the average relative error by approximately 20% and increases the proportion of unchanged shortest paths by about 10%. In summary, we aimed to address privacy issues in weighted social networks, providing an effective method to protect user-sensitive information while ensuring the accuracy and utility of data analysis.

TDASD: Generating medically significant fine-grained lung adenocarcinoma nodule CT images based on stable diffusion models with limited sample size.

BACKGROUND AND OBJECTIVES: Spread through air spaces (STAS) is an emerging lung cancer infiltration pattern. Predicting its spread through CT scans is crucial. However, limited STAS data makes this prediction task highly challenging. Stable diffusion is capable of generating more diverse and higher-quality images compared to traditional GAN models, surpassing the dominating GAN family models in image synthesis over the past few years. To alleviate the issue of limited STAS data, we propose a method TDASD based on stable diffusion, which is able to generate high-resolution CT images of pulmonary nodules corresponding to specific nodular signs according to the medical professionals. METHODS: First, we apply the stable diffusion method for fine-tuning training on publicly available lung datasets. Subsequently, we extract nodules from our hospital's lung adenocarcinoma data and apply slight rotations to the original nodule CT slices within a reasonable range before undergoing another round of fine-tuning through stable diffusion. Finally, employing DDIM and Ksample sampling methods, we generate lung adenocarcinoma nodule CT images with signs based on prompts provided by doctors. The method we propose not only safeguards patient privacy but also enhances the diversity of medical images under limited data conditions. Furthermore, our approach to generating medical images incorporates medical knowledge, resulting in images that exhibit pertinent medical features, thus holding significant value in tumor discrimination diagnostics. RESULTS: Our TDASD method has the capability to generate medically meaningful images by optimizing input prompts based on medical descriptions provided by experts. The images generated by our method can improve the model's classification accuracy. Furthermore, Utilizing solely the data generated by our method for model training, the test results on the original real dataset reveal an accuracy rate that closely aligns with the testing accuracy achieved through training on real data. CONCLUSIONS: The method we propose not only safeguards patient privacy but also enhances the diversity of medical images under limited data conditions. Furthermore, our approach to generating medical images incorporates medical knowledge, resulting in images that exhibit pertinent medical features, thus holding significant value in tumor discrimination diagnostics.

Privacy-Preserving Face Recognition Method Based on Randomization and Local Feature Learning.

Personal privacy protection has been extensively investigated. The privacy protection of face recognition applications combines face privacy protection with face recognition. Traditional face privacy-protection methods encrypt or perturb facial images for protection. However, the original facial images or parameters need to be restored during recognition. In this paper, it is found that faces can still be recognized correctly when only some of the high-order and local feature information from faces is retained, while the rest of the information is fuzzed. Based on this, a privacy-preserving face recognition method combining random convolution and self-learning batch normalization is proposed. This method generates a privacy-preserved scrambled facial image and an image fuzzy degree that is close to an encryption of the image. The server directly recognizes the scrambled facial image, and the recognition accuracy is equivalent to that of the normal facial image. The method ensures the revocability and irreversibility of the privacy preserving of faces at the same time. In this experiment, the proposed method is tested on the LFW, Celeba, and self-collected face datasets. On the three datasets, the proposed method outperforms the existing face privacy-preserving recognition methods in terms of face visual information elimination and recognition accuracy. The recognition accuracy is >99%, and the visual information elimination is close to an encryption effect.

Exploring the Impact of Security Technologies on Mental Health: A Comprehensive Review.

This comprehensive review explores the intricate relationship between security technologies and mental health. Security technologies, including physical security, cybersecurity, and surveillance measures, are integral components of our modern world, designed to protect individuals, organizations, and society from various threats. While they are vital in enhancing safety, they also have profound implications for mental well-being. The review delves into the positive impacts of security technologies, including their capacity to enhance personal safety, reduce anxiety and fear, and instill a sense of security. However, it also reveals the negative consequences, such as privacy invasion, surveillance-related stress, paranoia, and ethical concerns, which can erode mental health. User perception and trust are central to understanding how individuals experience security technologies. The review emphasizes the importance of ethical guidelines, user education, and technological advancements in mitigating negative impacts. By embracing an ethical-by-design approach, empowering users, and promoting public awareness, a balanced equilibrium between security and mental health can be achieved. The conclusion highlights the significance of ongoing research and interdisciplinary collaboration to navigate this intricate relationship effectively. By prioritizing ethical considerations and fostering a dialogue that values security and individual well-being, we can ensure a safer and more mentally healthy future in our technologically interconnected world.

Toward robust and privacy-enhanced facial recognition: A decentralized blockchain-based approach with GANs and deep learning.

In recent years, the extensive use of facial recognition technology has raised concerns about data privacy and security for various applications, such as improving security and streamlining attendance systems and smartphone access. In this study, a blockchain-based decentralized facial recognition system (DFRS) that has been designed to overcome the complexities of technology. The DFRS takes a trailblazing approach, focusing on finding a critical balance between the benefits of facial recognition and the protection of individuals' private rights in an era of increasing monitoring. First, the facial traits are segmented into separate clusters which are maintained by the specialized node that maintains the data privacy and security. After that, the data obfuscation is done by using generative adversarial networks. To ensure the security and authenticity of the data, the facial data is encoded and stored in the blockchain. The proposed system achieves significant results on the CelebA dataset, which shows the effectiveness of the proposed approach. The proposed model has demonstrated enhanced efficacy over existing methods, attaining 99.80% accuracy on the dataset. The study's results emphasize the system's efficacy, especially in biometrics and privacy-focused applications, demonstrating outstanding precision and efficiency during its implementation. This research provides a complete and novel solution for secure facial recognition and data security for privacy protection.

Medical report generation based on multimodal federated learning.

Medical image reports are integral to clinical decision-making and patient management. Despite their importance, the confidentiality and private nature of medical data pose significant issues for the sharing and analysis of medical image data. This paper addresses these concerns by introducing a multimodal federated learning-based methodology for medical image reporting. This methodology harnesses distributed computing for co-training models across various medical institutions. Under the federated learning framework, every medical institution is capable of training the model locally and aggregating the updated model parameters to curate a top-tier medical image report model. Initially, we advocate for an architecture facilitating multimodal federated learning, including model creation, parameter consolidation, and algorithm enhancement steps. In the model selection phase, we introduce a deep learning-based strategy that utilizes multimodal data for training to produce medical image reports. In the parameter aggregation phase, the federal average algorithm is applied to amalgamate model parameters trained by each institution, which leads to a comprehensive global model. In addition, we introduce an evidence-based optimization algorithm built upon the federal average algorithm. The efficacy of the proposed architecture and scheme is showcased through a series of experiments. Our experimental results validate the proficiency of the proposed multimodal federated learning approach in generating medical image reports. Compared to conventional centralized learning methods, our proposal not only enhances the protection of patient confidentiality but also enriches the accuracy and overall quality of medical image reports. Through this research, we offer a novel solution for the privacy issues linked with the sharing and analyzing of medical data. Expected to assume a crucial role in medical image report generation and other medical applications, the multimodal federated learning method is set to deliver more precise, efficient, and privacy-secured medical services for healthcare professionals and patients.

High Accuracy Open-Source Clinical Data De-Identification: The CliniDeID Solution.

Clinical data de-identification offers patient data privacy protection and eases reuse of clinical data. As an open-source solution to de-identify unstructured clinical text with high accuracy, CliniDeID applies an ensemble method combining deep and shallow machine learning with rule-based algorithms. It reached high recall and precision when recently evaluated with a selection of clinical text corpora.

Dual blockchain-based data sharing mechanism with privacy protection for medical internet of things.

In the period of big data, the Medical Internet of Things (MIoT) serves as a critical technology for modern medical data collection. Through medical devices and sensors, it enables real-time collection of a large amount of patients' physiological parameters and health data. However, these data are often generated in a high-speed, large-scale, and diverse manner, requiring integration with traditional medical systems, which further exacerbates the phenomenon of scattered and heterogeneous medical data. Additionally, the privacy and security requirements for the devices and sensor data involved in the MIoT are more stringent. Therefore, when designing a medical data sharing mechanism, the data privacy protection capability of the mechanism must be fully considered. This paper proposes an alliance chain medical data sharing mechanism based on a dual-chain structure to achieve secure sharing of medical data among entities such as medical institutions, research institutions, and cloud privacy centers, and at the same time provide privacy protection functions to achieve a balanced combination of privacy protection capability and data accessibility of medical data. First, a knowledge technology based on ciphertext policy attribute encryption with zero-knowledge concise non-interactive argumentation is used, combined with the data sharing structure of the federation chain, to ensure the integrity and privacy-protecting capability of medical data. Second, the approach employs certificate-based signing and proxy re-encryption technology, ensuring that entities can decrypt and verify medical data at the cloud privacy center using this methodology, consequently addressing the confidentiality concerns surrounding medical data. Third, an efficient and secure key identity-based encryption protocol is used to ensure the legitimacy of user identity and improve the security of medical data. Finally, the theoretical and practical performance analysis proves that the mechanism is feasible and efficient compared with other existing mechanisms.

PICOTEES: a privacy-preserving online service of phenotype exploration for genetic-diagnostic variants from Chinese children cohorts.

The growth in biomedical data resources has raised potential privacy concerns and risks of genetic information leakage. For instance, exome sequencing aids clinical decisions by comparing data through web services, but it requires significant trust between users and providers. To alleviate privacy concerns, the most commonly used strategy is to anonymize sensitive data. Unfortunately, studies have shown that anonymization is insufficient to protect against reidentification attacks. Recently, privacy-preserving technologies have been applied to preserve application utility while protecting the privacy of biomedical data. We present the PICOTEES framework, a privacy-preserving online service of phenotype exploration for genetic-diagnostic variants (https://birthdefectlab.cn:3000/). PICOTEES enables privacy-preserving queries of the phenotype spectrum for a single variant by utilizing trusted execution environment technology, which can protect the privacy of the user's query information, backend models, and data, as well as the final results. We demonstrate the utility and performance of PICOTEES by exploring a bioinformatics dataset. The dataset is from a cohort containing 20,909 genetic testing patients with 3,152,508 variants from the Children's Hospital of Fudan University in China, dominated by the Chinese Han population (>99.9%). Our query results yield a large number of unreported diagnostic variants and previously reported pathogenicity.

On Privacy Protection of Electronic Health Records / 中国医学伦理学

With the continuous advancement of health informatization and the wide application of medical big data, electronic health records came into being and spread rapidly. However, because electronic health records contain a large amount of private information, privacy protection is the primary consideration for the sustainable development of electronic health records. By analyzing the shortcomings of privacy protection of electronic health records in law, technology, management and protection consciousness, this paper put forward some countermeasures, such as perfecting the relevant laws and regulations of privacy protection of electronic health records, improving the technical level, improving the management defects of electronic health records, and cultivating the privacy protection consciousness of professionals and the public, so as to improve the overall privacy protection level of China’s health records information management system and provide effective protection for the privacy information of Chinese residents’ electronic health records.

GLPS: A Geohash-Based Location Privacy Protection Scheme.

With the development of mobile applications, location-based services (LBSs) have been incorporated into people's daily lives and created huge commercial revenues. However, when using these services, people also face the risk of personal privacy breaches due to the release of location and query content. Many existing location privacy protection schemes with centralized architectures assume that anonymous servers are secure and trustworthy. This assumption is difficult to guarantee in real applications. To solve the problem of relying on the security and trustworthiness of anonymous servers, we propose a Geohash-based location privacy protection scheme for snapshot queries. It is named GLPS. On the user side, GLPS uses Geohash encoding technology to convert the user's location coordinates into a string code representing a rectangular geographic area. GLPS uses the code as the privacy location to send check-ins and queries to the anonymous server and to avoid the anonymous server gaining the user's exact location. On the anonymous server side, the scheme takes advantage of Geohash codes' geospatial gridding capabilities and GL-Tree's effective location retrieval performance to generate a k-anonymous query set based on user-defined minimum and maximum hidden cells, making it harder for adversaries to pinpoint the user's location. We experimentally tested the performance of GLPS and compared it with three schemes: Casper, GCasper, and DLS. The experimental results and analyses demonstrate that GLPS has a good performance and privacy protection capability, which resolves the reliance on the security and trustworthiness of anonymous servers. It also resists attacks involving background knowledge, regional centers, homogenization, distribution density, and identity association.