Figure - available from: Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery
This content is subject to copyright. Terms and conditions apply.
Source publication
Data mining (DM) and machine learning (ML) applications in medical diagnostic systems are budding. Data privacy is essential in these systems as healthcare data are highly sensitive. The proposed work first discusses various privacy and security challenges in these systems. To address these next, we discuss different privacy‐preserving (PP) computa...
Similar publications
Federated learning is a widely used distributed learning approach in recent years, however, despite model training from collecting data become to gathering parameters, privacy violations may occur when publishing and sharing models. A dynamic approach is proposed to add Gaussian noise more effectively and apply differential privacy to federal deep...
Citations
... The Institute of Medicine (IOM) emphasized these challenges in its report titled "To Err is Human: Building a Safer Health System," highlighting issues related to patient safety and the impact of diagnostic errors on patient care. Health and well-being are undeniably among the most fundamental concerns for humanity, as evidenced by the substantial size and rapid growth of the global healthcare industry, projected to exceed 10 trillion dollars by 2022 [15]. Artificial intelligence (AI) and its integration with machine learning (ML) represent one of the most promising technological advancements poised to elevate this rapidly expanding industry, offering the potential to enhance healthcare and improve patient outcomes [16]. ...
... Moreover, recall of the developed BOA-DRNN strategy is calculated in following eqn. (15) ...
The healthcare industry has witnessed an unprecedented integration of unstructured data from diverse sources including medical images, clinical notes, patient records, etc. Traditional methods often struggle to effectively analyze and make sense of this heterogeneous data. In response to the growing integration of diverse unstructured healthcare data, this study introduces a novel approach leveraging a hybrid model that combines Deep Recurrent Neural Network and Butterfly Optimization Algorithm (BOA-DRNN). The proposed study aims is to enhance the analysis of complex and unstructured healthcare data by examining hierarchical representations and temporal dependencies. The proposed mechanism begins with the collection and pre-processing of unstructured healthcare data. The DRNN component examines the hierarchical representations and temporal dependencies within the unstructured data. By capturing patterns in the data, the DRNN facilitates improved predictive analysis and offers enhanced decision-making within healthcare units. In addition, the BOA approach was utilized for optimizing the DRNN training by fine-tuning its hyperparameters. This optimized training of DRNN ensures greater effective analysis of data and provides improved prediction performances. The presented framework was validated with the publicly available unstructured healthcare dataset and the results are examined in terms of accuracy, precision, recall and f-measure.
... Another technology worth investigating is Software-Defined Networking (SDN), which enables dynamic network management and control, thereby strengthening security measures in PHM architectures [25]- [27] In addition, various approaches have been explored to address privacy concerns in PHM architectures [4], [15], [16], [28], such as differential privacy [14], homomorphic encryption [22], and privacy-aware anonymity-based techniques [18]. These approaches offer promising avenues to protect sensitive health data and enhance privacy in PHM architectures. ...
Pervasive Health Monitoring (PHM) uses sensors and wearable devices and data analytics for real-time health monitoring. It enables early detection and personalized care interventions. This technology has the potential to revolutionize healthcare by improving proactive and preventive care.
Besides, Deep learning (DL) based PHM is even more promising as it improves the discovery of complex patterns and correlations. This leads to precise health monitoring and personalized care, enhances diagnostics, and ultimately improves patient outcomes in the field of healthcare.
However, privacy and security considerations must be addressed for successful implementation. This paper investigates the security and privacy concerns in Pervasive Health Monitoring architectures. It discusses through an illustrative DL-based PHM architecture the potential threats and attacks during the inference and training phases, and identifies key security and privacy issues. It also gives insights on countermeasures and technological solutions that can address security and privacy concerns in PHM architectures.
... There exists a plethora of survey articles on privacy-preserving data mining (PPDM) for a variety of applications such as cloud computing, location-based services, e-health, recommender systems, transport data, and internet of things [24][25][26][27][28]. In PPDM, privacy is ensured by applying the anonymization method while minimally changing the semantics of the data [25]. ...
Anonymization techniques are widely used to make personal data broadly available for analytics/data-mining purposes while preserving the privacy of the personal information enclosed in it. In the past decades, a substantial number of anonymization techniques were developed based on the famous four privacy models such as k-anonymity, ℓ-diversity, t-closeness, and differential privacy. In recent years, there has been an increasing focus on developing attribute-centric anonymization methods, i.e., methods that exploit the properties of the underlying data to be anonymized to improve privacy, utility, and/or computing overheads. In addition, synthetic data are also widely used to preserve privacy (privacy-enhancing technologies), as well as to meet the growing demand for data. To the best of the authors’ knowledge, none of the previous studies have covered the distinctive features of attribute-centric anonymization methods and synthetic data based developments. To cover this research gap, this paper summarizes the recent state-of-the-art (SOTA) attribute-centric anonymization methods and synthetic data based developments, along with the experimental details. We report various innovative privacy-enhancing technologies that are used to protect the privacy of personal data enclosed in various forms. We discuss the challenges and the way forward in this line of work to effectively preserve both utility and privacy. This is the first work that systematically covers the recent development in attribute-centric and synthetic-data-based privacy-preserving methods and provides a broader overview of the recent developments in the privacy domain.
... The above three categories are presented in Table 3, Table 4, and Table 5 for privacypreserving computation techniques at various stages (Input(test data), output, model, and training data privacy). Naresh and Thamarai (2023) also analyzed the privacy-preserving Machine Learning techniques and discussed sensitive data privacy at various stages in the learning models. ...
Deep Learning (DL) has already shown tremendous potential in designing intelligent clinical support systems in biomedicine. Data privacy plays a significant role while training and testing DL models, especially for sensitive data. Privacy-Preserving Deep Learning (PPDL) applications in Healthcare are rapidly growing as medical informatics deals with sensitive data. This work reviews the recent advances in PPDL techniques in Healthcare. It first analyzes the need of PPDL in healthcare informatics using a threat model and then discusses privacy-preserving computation techniques for secure data processing and evaluation. Next, it focuses on DL applications over Healthcare in three categories: (i) PPDL in the private cloud, (ii) PPDL in the public cloud, and (iii) privacy based on modifications in DL architectures. Next, we examine data privacy at different stages of DL deployment in Healthcare, including input, model, training, and output. We also provide a summary of the evaluation outcomes of the solutions reviewed. Additionally, we highlight the unique challenges in PPDL for Healthcare and offer suggestions for future research directions.
... Despite the fact that health data offers enormous opportunities in various fields, maintaining the privacy of health data still poses several unresolved privacy and security challenges [29]- [31]. In the following, we present some wellestablished privacy models that are used to ensure privacy of health data. ...
Advances in data collection, storage, and processing in e-Health systems have recently increased the importance and popularity of data mining in the health care field. However, the high sensitivity of the handled and shared data, brings a high risk of information disclosure and exposure. It is therefore important to hide sensitive relationships by modifying the shared data. This major information security threat has, therefore, mandated the requirement of hiding/securing sensitive relationships of shared data. As a large number of data mining activities that attempt to identify interesting patterns from databases depend on locating frequent item sets, further investigation of frequent item sets requires privacy-preserving techniques. To solve many difficult combinatorial problems, such as data distribution problem, exact and heuristic algorithms have been used. Exact algorithms are studied and considered optimal for such problems, however they suffer scalability bottleneck, as they are limited to medium-sized instances only. Heuristic algorithms, on the other hand, are scalable, however, they perform poor on security and privacy preservation. This paper proposes a novel heuristic approach based on Formal Concept Analysis (FCA) for enhancing security and privacy preservation of sensitive e-Health information using itemset hiding techniques. Our approach, named FACHS (FCA Hiding Sensitive-itemsets) uses constraints to minimise side effects and asymmetry between the original database and the clean database (minimal distortion on the database). Moreover, our approach does not require frequent itemset extraction before the masking process. This gives the proposed approach an advantage in terms of total availability. We tested our FCAHS heuristic on various reference datasets. Extensive experimental results showed the effectiveness of the proposed masking approach and the time efficiency of itemset extraction, making it very promising for e-Health sensitive data security and privacy.
Future connected and autonomous vehicles (CAVs) must be secured against cyberattacks for their everyday functions on the road so that safety of passengers and vehicles can be ensured. This article presents a holistic review of cybersecurity attacks on sensors and threats regarding multi‐modal sensor fusion. A comprehensive review of cyberattacks on intra‐vehicle and inter‐vehicle communications is presented afterward. Besides the analysis of conventional cybersecurity threats and countermeasures for CAV systems, a detailed review of modern machine learning, federated learning, and blockchain approach is also conducted to safeguard CAVs. Machine learning and data mining‐aided intrusion detection systems and other countermeasures dealing with these challenges are elaborated at the end of the related section. In the last section, research challenges and future directions are identified.
This article is categorized under: Commercial, Legal, and Ethical Issues > Security and Privacy
Technologies > Machine Learning
Technologies > Internet of Things
Deep learning (DL) can be considered as a powerful tool in different fields and for different applications but its importance raised the concern about privacy, security, and defense issues. This research presents an important overview about different aspects and state-of-the-art techniques in DL privacy, security, and defense. Wide range of topics was covered including private data frameworks, different types of threats and attacks, and the most important defense techniques. We have also discussed the challenges and limitations of each approach besides to possible future research directions. This survey can be considered as a comprehensive guide for other researchers and policymakers who are interested in understanding these important topics associated with DL.
