A Machine Learning Approach for the NLP-Based Analysis of Cyber Threats and Vulnerabilities of the Healthcare Ecosystem
Open accessThe DOI matches its Crossref record; 47 of the 48 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Digitization in healthcare systems, with the wid adoption of Electronic Health Records, connected medical devices, software and systems providing efficient healthcare service delivery and management. On the other hand, the use of these systems has significantly increased cyber threats in the healthcare sector. Vulnerabilities in the existing and legacy systems are one of the key causes for the threats and related risks. Understanding and addressing the threats from the connected medical devices and other parts of the ICT health infrastructure are of paramount importance for ensuring security within the overall healthcare ecosystem. Threat and vulnerability analysis provides an effective way to lower the impact of risks relating to the existing vulnerabilities. However, this is a challenging task due to the availability of massive data which makes it difficult to identify potential patterns of security issues. This paper contributes towards an effective threats and vulnerabilities analysis by adopting Machine Learning models, such as the BERT neural language model and XGBoost, to extract updated information from the Natural Language documents largely available on the web, evaluating at the same time the level of the identified threats and vulnerabilities that can impact on the healthcare system, providing the required information for the most appropriate management of the risk. Experiments were performed based on CS news extracted from the Hacker News website and on Common Vulnerabilities and Exposures (CVE) vulnerability reports. The results demonstrate the effectiveness of the proposed approach, which provides a realistic manner to assess the threats and vulnerabilities from Natural Language texts, allowing adopting it in real-world Healthcare ecosystems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures










Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Applications in healthcare and smart policing demonstrate NLP's versatility, with BERT analyzing vulnerabilities for 88.45% accuracy [22,73].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [22]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Integration gaps are acknowledged in research gaps [12], with calls for federated datasets [22] to enhance privacy and realism, yet practical implementations remain scarce.”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [22]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“privacy constraints limited anonymized real data availability [4,22]”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [22]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“NLP for fraud detection in transaction narratives [22] handles volume but struggles with adversarial attacks”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [22]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“privacy-preserving federated learning [22] mitigates data leaks but increases latency by 20-30% in real-time financial monitoring [4]”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [22]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Recently, the Transformer-based architectures [38], such as BERT [39], were also leveraged in the CS domain, in particular for the definition of NER methodologies, able, among other things, to identify threats, vulnerabilities, and attacks mentioned in unstructured natural language texts.”
MethodBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 3×
“Recently, the Transformer-based architectures [38], such as BERT [39], were also leveraged in the CS domain, in particular for the definition of NER methodologies, able, among other things, to identify threats, vulnerabilities, and attacks mentioned in unstructured natural language texts.”
MethodXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Recently, the Transformer-based architectures [38], such as BERT [39], were also leveraged in the CS domain, in particular for the definition of NER methodologies, able, among other things, to identify threats, vulnerabilities, and attacks mentioned in unstructured natural language texts.”
MethodEfficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 1×
“We also considered in the future works to test word embeddings [48]”
BackgroundEnriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 3×
“Other planned tests include the adoption of the feature representation of the ML model of the Vulnerability Assessment step based on word embedding models, such as word2vec or FastText.”
MethodInfluentialBioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218 · cited 1×
“In our experimental assessment, we adopted SecBERT, which is based on classic BERT architecture, because it is shown in the literature that the pretraining on a closed-domain corpus is able to improve the performance of a neural language model when it is fine-tuned on tasks of the same domain [35,54].”
Methodboyd, D., & Crawford, K. (2012) · Information, Communication & Society · doi:10.1080/1369118x.2012.678878 · Cited by 5,479 · cited 1×
“According to [14], researchers need to deeply investigate ethical compliance even when the data seem to be public.”
BackgroundAn information-theoretic perspective of tf–idf measures
Aizawa, A. (2003) · Information Processing & Management · doi:10.1016/s0306-4573(02)00021-3 · Cited by 1,419 · cited 5×
“Notably, TF-IDF is considered as a statistical measure that computes how relevant a word is to a document in a collection of documents.”
MethodInfluentialFLAIR: An Easy-to-Use Framework for State-of-the-Art NLP
Akbik, A., Bergmann, T., Blythe, D. A. J., Rasul, K., Schweter, S., & Vollgraf, R. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-4010 · Cited by 1,175 · cited 1×
“In particular, it integrates regular expressions and KBs, a ML-based model for generic domain entities and a Flair-based [43] NER model.”
MethodPacemakers and Implantable Cardiac Defibrillators: Software Radio Attacks and Zero-Power Defenses
Halperin, D., Heydt-Benjamin, T. S., Ransford, B., Clark, S. S., Defend, B., Morgan, W., Fu, K., Kohno, T., & Maisel, W. H. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.31 · Cited by 743
Root mean square error or mean absolute error? Use their ratio as well
Karunasingha, D. S. K. (2022) · Information Sciences · doi:10.1016/j.ins.2021.11.036 · Cited by 730
Challenges in deploying machine learning: A survey of case studies
Paleyes, A., Urma, R.-G., & Lawrence, N. D. (2023) · ACM Computing Surveys · doi:10.1145/3533378 · Cited by 638 · cited 1×
“Moreover, the deployment of ML-based systems in critical environments, such as the HCII, further complicates this scenario, due to the difficulties of acquiring and managing the data from the target environment and integrating the ML technologies within the existing HCII systems [24].”
Cybersecurity in healthcare: A narrative review of trends, threats and ways forward
Coventry, L., & Branley, D. (2018) · Maturitas · doi:10.1016/j.maturitas.2018.04.008 · Cited by 479 · cited 2×
“There are significant numbers of connected devices within the healthcare system [3] and vulnerabilities within these connected devices can propagate to other parts of the network [4].”
BackgroundGhaffarian, S. M., & Shahriari, H. R. (2018) · ACM Computing Surveys · doi:10.1145/3092566 · Cited by 353 · cited 2×
“[29] Review on ML and Data Mining techniques for software vulnerabilities Vulnerability prediction based on text mining on software source code produced better result than metrics-based work despite availability of metrics.”
BackgroundMethodInfluence of Human Factors on Cyber Security within Healthcare Organisations: A Systematic Review
Nifakos, S., Chandramouli, K., Nikolaou, C. K., Papachristou, P., Koch, S., Panaousis, E., & Bonacina, S. (2021) · Sensors · doi:10.3390/s21155119 · Cited by 247 · cited 1×
“Furthermore, human factors have a crucial impact on the CS within Healthcare Organizations [7].”
BackgroundDeep Learning Algorithms for Cybersecurity Applications: A Technological and Status Review
Dixit, P., & Silakari, S. (2021) · Computer Science Review · doi:10.1016/j.cosrev.2020.100317 · Cited by 241 · cited 1×
“The implementation of end-to-end ML technologies for the identification, analysis and assessment of CS issues is still a challenging task, due to some implicit limits of ML, such as the need for large and trustable datasets, the lack of explainability of many models, and the computational power required [23].”
BackgroundCybersecurity of Hospitals: discussing the challenges and working towards mitigating the risks
Argaw, S. T., Troncoso-Pastoriza, J. R., Lacey, D., Florin, M.-V., Calcavecchia, F., Anderson, D., Burleson, W., Vogel, J.-M., O’Leary, C., Eshaya-Chauvin, B., et al. (2020) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-020-01161-7 · Cited by 231
Mavroeidis, V., & Bromander, S. (2017) · 2017 European Intelligence and Security Informatics Conference (EISIC) · doi:10.1109/eisic.2017.20 · Cited by 213 · cited 2×
“Threat intelligence within the cyber security domain provides a knowledge base for threat-related information and includes mechanism to present this this knowledge, such as taxonomies, sharing standards, and ontologies [19], which can be exploited to implement information extraction methods [34] specifically customise…”
BackgroundMethodA Survey of Machine Learning-Based Solutions for Phishing Website Detection
Tang, L., & Mahmoud, Q. H. (2021) · Machine Learning and Knowledge Extraction · doi:10.3390/make3030034 · Cited by 187 · cited 1×
“Machine Learning-based algorithms, such as eXtreme Gradient Boosting [20], have been also successfully applied to classify textual documents in CS domain [21,22].”
MethodDeep neural network for hierarchical extreme multi-label text classification
Gargiulo, F., Silvestri, S., Ciampi, M., & de Pietro, G. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.03.041 · Cited by 143 · cited 5×
“The high Accuracy values have been obtained due to the very high number of true negatives tnci , which is related to the dataset features (see previous Table 6), where the number of entities is very small if compared to the number of words that are not an entity.”
MethodSelf-citationOn the use of r and r squared in correlation and regression
Kasuya, E. (2018) · Ecological Research · doi:10.1111/1440-1703.1011 · Cited by 117 · cited 1×
“The Mean Absolute Error (MAE), Mean Squared Error (MSE) [60] and R-Squared (R2) [61], defined in the equations below, were used as performance metrics to evaluate the performance of the proposed automated vulnerability scoring system based on the two supervised machine learning models, namely multiclass logistic regre…”
MethodCASIE: Extracting Cybersecurity Event Information from Text
Satyapanich, T., Ferraro, F., & Finin, T. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6401 · Cited by 112
Ma, P., Jiang, B., Lu, Z., Li, N., & Jiang, Z. (2021) · Tsinghua Science and Technology · doi:10.26599/tst.2019.9010033 · Cited by 94 · cited 2×
“The authors of [15] presented an NLP DL-based architecture for the identification of relevant CS information, such as vulnerability exploitations, attack discoveries and advanced persistent threats.”
BackgroundMethodCyBERT: Cybersecurity Claim Classification by Fine-Tuning the BERT Language Model
Ameri, K., Hempel, M., Sharif, H., Lopez Jr., J., & Perumalla, K. (2021) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp1040031 · Cited by 76
Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study
Fu, J., Liu, P., & Zhang, Q. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6276 · Cited by 69
Analyzing the Perceived Severity of Cybersecurity Threats Reported on Social Media
Zong, S., Ritter, A., Mueller, G., & Wright, E. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1140 · Cited by 68 · cited 2×
“The authors of one paper [32] presented a method to analyze the severity of CS threats analyzing the language of CS-related tweets through a DL approach.”
MethodUsing BERT and Augmentation in Named Entity Recognition for Cybersecurity Domain
Tikhomirov, M. M., Loukachevitch, N., Sirotina, A., & Dobrov, B. V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-51310-8_2 · Cited by 63 · cited 1×
“In particular, the complexity of the NL can present polysemy, irony, long sentences and other issues, in addition to the peculiarities the technical language used CS domain, which uses many non-standard abbreviations or acronyms [10].”
BackgroundIdentification of Cybersecurity Specific Content Using the Doc2Vec Language Model
Mendsaikhan, O., Hasegawa, H., Yamaguchi, Y., & Shimada, H. (2019) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac.2019.00064 · Cited by 61 · cited 1×
“Mining and extracting the most updated CS threats and vulnerabilities from the huge amount of information available in NL documents on the Internet can support the establishment of situational awareness proactively monitoring and preventing CS issues [11], but specifically tailored approaches are required [12].”
BackgroundUnsupervised entity and relation extraction from clinical records in Italian
Alicante, A., Corazza, A., Isgrò, F., & Silvestri, S. (2016) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2016.01.014 · Cited by 59 · cited 1×
“For instance, the identification of the assets and threats of the HCII could be refined by applying Relation Extraction techniques [62], in order to better identify (and the corresponding pairs) and classify the relation between them, improving the calculation of their occurrence.”
MethodSelf-citationData and knowledge-driven named entity recognition for cyber security
Gao, C., Zhang, X., & Liu, H. (2021) · Cybersecurity · doi:10.1186/s42400-021-00072-y · Cited by 57 · cited 1×
“[15,18] Cyber Security information/entity identification NLP DL-based architecture is used for Named Entity Recognition (NER) in cyber security based on unstructured NER dataset.”
MethodNikoloudakis, Y., Kefaloukos, I., Klados, S., Panagiotakis, S., Pallis, E., Skianis, C. A., & Markakis, E. (2021) · Sensors · doi:10.3390/s21144939 · Cited by 54 · cited 1×
“[36], a ML-based situational awareness framework is presented which is able to detect existing and newly introduced network-enabled entities in an IoT-based environment based on real-time awareness features provided by the Software-Defined Networking (SDN) paradigm, assessing them against known vulnerabilities, and as…”
MethodPhandi, P., Silva, A., & Lu, W. (2018) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/s18-1113 · Cited by 44 · cited 3×
“Phandi, P.; Silva, A.; Lu, W. SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP).”
MethodInfluentialNamed Entity Recognition Using BERT with Whole World Masking in Cybersecurity Domain
Zhou, S., Liu, J., Zhong, X., & Zhao, W. (2021) · 2021 IEEE 6th International Conference on Big Data Analytics (ICBDA) · doi:10.1109/icbda51983.2021.9403180 · Cited by 42 · cited 2×
“[16] Cyber Security NER CS NER model that integrates BERT and BiLSTM-CRF architectures, improving baseline performance.”
MethodCyber Security Vulnerability Detection Using Natural Language Processing
Singh, K., Grover, S. S., & Kumar, R. K. (2022) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot54504.2022.9817336 · Cited by 34 · cited 2×
“[37] Software code vulnerability detection Automated software vulnerability detection using recent DL approaches.”
MethodJoint BERT Model based Cybersecurity Named Entity Recognition
Chen, Y., Ding, J., Li, D., & Chen, Z. (2021) · International Conference on Software Engineering and Information Management (ICSIM) · doi:10.1145/3451471.3451508 · Cited by 30 · cited 2×
“[17] Cyber Security NER A BERT-based model fine-tuned for the CS NER task.”
MethodVulnerability prediction for secure healthcare supply chain service delivery
Islam, S., Abba, A., Ismail, U. M., Mouratidis, H., & Papastergiou, S. (2022) · Integrated Computer-Aided Engineering · doi:10.3233/ica-220689 · Cited by 29 · cited 1×
“However, despite these benefits, the adoption of digital technology provides many Cyber Security (CS) challenges that can pose any potential risks within the healthcare system [1].”
BackgroundSelf-citationIterative Annotation of Biomedical NER Corpora with Deep Neural Networks and Knowledge Bases
Silvestri, S., Gargiulo, F., & Ciampi, M. (2022) · Applied Sciences · doi:10.3390/app12125775 · Cited by 26 · cited 2×
“We adopted an iterative hybrid Distant Supervision (DS) and Active Learning (AL) approach for the annotation of the CS NER training set proposed in [45], which leverages the knowledge extracted from these KBs in the DS phase.”
MethodSelf-citationCyberattack Path Generation and Prioritisation for Securing Healthcare Systems
Islam, S., Papastergiou, S., Kalogeraki, E.-M., & Kioskli, K. (2022) · Applied Sciences · doi:10.3390/app12094443 · Cited by 24
Self-citationCyber Supply Chain Threat Analysis and Prediction Using Machine Learning and Ontology
Yeboah-Ofori, A., Mouratidis, H., Ismai, U., Islam, S., & Papastergiou, S. (2021) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-79150-6_41 · Cited by 22
Self-citationImproving Biomedical Information Extraction with Word Embeddings Trained on Closed-Domain Corpora
Silvestri, S., Gargiulo, F., & Ciampi, M. (2019) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc47284.2019.8969769 · Cited by 15 · cited 3×
“These models can be trained on the available closed-domain CS corpora formed by the large document collections obtained within the development and experimental assessment of the proposed methodologies, improving the effectiveness of the vector spaces [35].”
MethodSelf-citationMalware Detection based on Cascading XGBoost and Cost Sensitive
Wu, D. J., Guo, P., & Wang, P. W. (2020) · International Conference on Computer Communication and Network Security (CCNS) · doi:10.1109/ccns50731.2020.00051 · Cited by 14 · cited 1×
“Machine Learning-based algorithms, such as eXtreme Gradient Boosting [20], have been also successfully applied to classify textual documents in CS domain [21,22].”
MethodA distributed architecture to integrate ontological knowledge into information extraction
Alicante, A., Benerecetti, M., Corazza, A., & Silvestri, S. (2016) · International Journal of Grid and Utility Computing · doi:10.1504/ijguc.2016.081011 · Cited by 12
Self-citationCyber Threat Analysis Using Natural Language Processing for a Secure Healthcare System
Islam, S., Papastergiou, S., & Silvestri, S. (2022) · Proceedings - IEEE Symposium on Computers and Communications/IEEE Symposium on Computers and Communications · doi:10.1109/iscc55528.2022.9912768 · Cited by 12 · cited 1×
“A preliminary threat assessment approach has been already presented in [44] and its evolution and improvements are described in this paper.”
BackgroundSelf-citationChallenges of using machine learning algorithms for cybersecurity
Lima, A. Q., & Keegan, B. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-819204-7.00003-8 · Cited by 11
A Dynamic Cyber Security Situational Awareness Framework for Healthcare ICT Infrastructures
Islam, S., Papastergiou, S., & Mouratidis, H. (2021) · Panhellenic Conference on Informatics · doi:10.1145/3503823.3503885 · Cited by 10 · cited 2×
“For instance, a cyber-attack on insecure imaging servers and unprotected data storages supporting medical x-rays can lead to the web exposure of sensitive information of patients, such as medical images and scans; or a comptonisation of a remote monitoring software of defibrillators could allow adversaries to take adv…”
BackgroundSelf-citationAddressing Security Issues of Electronic Health Record Systems through Enhanced SIEM Technology
Sarno, C. D., Formicola, V., Sicuranza, M., & Paragliola, G. (2013) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1109/ares.2013.85 · Cited by 9 · cited 2×
“– n_estimators: [100, 400, 800] – max_depth: [3, 6, 9] – learning_rate: [0.”
BackgroundSome lessons learned using health data literature for smart information retrieval
Ciampi, M., Pietro, G. D., Masciari, E., & Silvestri, S. (2020) · ACM Symposium on Applied Computing · doi:10.1145/3341105.3374128 · Cited by 4 · cited 1×
“Mining and extracting the most updated CS threats and vulnerabilities from the huge amount of information available in NL documents on the Internet can support the establishment of situational awareness proactively monitoring and preventing CS issues [11], but specifically tailored approaches are required [12].”
BackgroundSelf-citation
Research works printed but not linked: 3
- Haque N.I. Rahman M.A. Shahriar M.H. Khalil A.A. Uluagac A.S. A Novel Framework for Threat Analysis of Machine Learning-based Smart Healthcare Systems arXiv 2021 2103.03472
- Alam M.T. Bhusal D. Park Y. Rastogi N. CyNER: A Python Library for Cybersecurity Named Entity Recognition arXiv 2022 2204.05754
- Liu Y. Ott M. Goyal N. Du J. Joshi M. Chen D. Levy O. Lewis M. Zettlemoyer L. Stoyanov V. RoBERTa: A Robustly Optimized BERT Pretraining Approach arXiv 2019 1907.11692
Cited by
Ferrag, M. A., Ndhlovu, M., Tihanyi, N., Cordeiro, L. C., Debbah, M., Lestable, T., & Thandi, N. S. (2024) · IEEE Access · doi:10.1109/access.2024.3363469 · Cited by 312
“In this context, Natural Language Processing (NLP) techniques are gaining attention as a promising approach for cyber threat detection [3].”
BackgroundFrom Vulnerability to Defense: The Role of Large Language Models in Enhancing Cybersecurity
Kasri, W., Himeur, Y., Alkhazaleh, H. A., Tarapiah, S., Atalla, S., Mansoor, W., & Al-Ahmad, H. (2025) · Computation · doi:10.3390/computation13020030 · Cited by 70
AI-Integrated Technology for a Secure and Ethical Healthcare Ecosystem
Boopathi, S., & Khang, A. (2023) · Advances in medical technologies and clinical practice book series · doi:10.4018/979-8-3693-0876-9.ch003 · Cited by 69
Silvestri, S., Islam, S., Amelin, D., Weiler, G., Papastergiou, S., & Ciampi, M. (2024) · International Journal of Information Security · doi:10.1007/s10207-023-00769-w · Cited by 50
“In previous experiments described in [13], a training set and a test set for the NER module were created, randomly selecting a subset of the dataset and then using a semisupervised annotation methodology based on an iterative application of DS and AL, incrementally described and improved in [12,…”
InfluentialSelf-citationKioskli, K., Fotis, T. G., Nifakos, S., & Mouratidis, H. (2023) · Applied Sciences · doi:10.3390/app13063410 · Cited by 83
“…additions from the literature include a contribution towards vulnerabilities and effective threats analysis by using machine learning models (i.e., BERT neural language model and XGBoost) to withdraw the most relevant information from the Natural Language documents mostly available online [21].”
Method
Metadata
- Authors
- Silvestri, S., Islam, S., Papastergiou, S., Tzagkarakis, C., & Ciampi, M.
- Affiliations
- Institute for High Performance Computing and Networking (IT)
- Anglia Ruskin University (GB)
- University of Piraeus (GR)
- Foundation for Research and Technology Hellas (GR)
- Corresponding author
- Silvestri, Stefano
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2023-01-06
- Volume
- 23
- Issue
- 2
- Pages
- 651
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9866080
- OpenAlex
- W4313648836
- Semantic Scholar
- 7e4bca67428c3b9487df550c65b36146ed278894
- Cited by
- 76
- References
- 45
- Citations by year
- 2026: 18 · 2025: 22 · 2024: 22 · 2023: 14
- FWCI
- 17.84
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Anglia Ruskin Research Online (Anglia Ruskin University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- Funders
- European Commission (883273)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Physical Sciences › Computer Science › Information Systems › Web Application Security Vulnerabilities
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- healthcare cybersecurity, cyber threats, software vulnerabilities, natural language processing, BERT, XGBoost, Hacker News, connected medical devices, electronic health records, security risk management
- MeSH terms
- Machine Learning, Delivery of Health Care, Computer Security, Ecosystem, Electronic Health Records
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.