Network and cybersecurity applications of defense in adversarial attacks: A state-of-the-art using machine learning and deep learning methods

Journal of Intelligent Systems, Год журнала: 2024, Номер 33(1)

Опубликована: Янв. 1, 2024

Abstract This study aims to perform a thorough systematic review investigating and synthesizing existing research on defense strategies methodologies in adversarial attacks using machine learning (ML) deep methods. A methodology was conducted guarantee literature analysis of the studies sources such as ScienceDirect, Scopus, IEEE Xplore, Web Science. question shaped retrieve articles published from 2019 April 2024, which ultimately produced total 704 papers. rigorous screening, deduplication, matching inclusion exclusion criteria were followed, hence 42 included quantitative synthesis. The considered papers categorized into coherent classification including three categories: security enhancement techniques, attack mechanisms, innovative mechanisms solutions. In this article, we have presented comprehensive earlier opened door potential future by discussing depth four challenges motivations attacks, while recommendations been discussed. science mapping also performed reorganize summarize results address issues trustworthiness. Moreover, covers large variety network cybersecurity applications subjects, intrusion detection systems, anomaly detection, ML-based defenses, cryptographic techniques. relevant conclusions well demonstrate what achieved against attacks. addition, revealed few emerging tendencies deficiencies area be remedied through better more dependable mitigation methods advanced persistent threats. findings crucial implications for community researchers, practitioners, policy makers artificial intelligence applications.

Язык: Английский

---

An integrated design concept evaluation method based on fuzzy weighted zero inconsistency and combined compromise solution considering inherent uncertainties

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103097 - 103097

Опубликована: Янв. 21, 2025

Язык: Английский

---

Fuzzy Decision‐Making Framework for Evaluating Hybrid Detection Models of Trauma Patients

Expert Systems, Год журнала: 2025, Номер 42(3)

Опубликована: Фев. 13, 2025

ABSTRACT This study introduces a new multi‐criteria decision‐making (MCDM) framework to evaluate trauma injury detection models in intensive care units (ICUs). research addresses the challenges associated with diverse machine learning (ML) models, inconsistencies, conflicting priorities, and importance of metrics. The developed methodology consists three phases: dataset identification pre‐processing, hybrid model development, an evaluation/benchmarking framework. Through meticulous is tailored focus on adult patients. Forty were by combining eight ML algorithms four filter‐based feature‐selection methods principal component analysis (PCA) as dimensionality reduction method, these evaluated using seven weight coefficients for metrics are determined 2‐tuple Linguistic Fermatean Fuzzy‐Weighted Zero‐Inconsistency (2TLF‐FWZIC) method. Vlsekriterijumska Optimizcija I Kompromisno Resenje (VIKOR) approach applied rank models. According 2TLF‐FWZIC, classification accuracy (CA) precision obtained highest weights 0.2439 0.1805, respectively, while F1, training time, test time lowest 0.1055, 0.0886, 0.1111, respectively. benchmarking results revealed following top‐performing models: Gini index logistic regression (GI‐LR), decision tree (GI_DT), information gain (IG_DT), VIKOR Q score values 0.016435, 0.023804, 0.042077, proposed MCDM assessed examined systematic ranking, sensitivity analysis, validation best‐selected two unseen datasets, mode explainability SHapley Additive exPlanations (SHAP) We benchmarked against other benchmark studies achieved 100% across six key areas. provides several insights into empirical synthesis this study. It contributes advancing medical informatics enhancing understanding selection ICUs.

Язык: Английский

---

Using Information Technology for Comprehensive Analysis and Prediction in Forensic Evidence

Deleted Journal, Год журнала: 2024, Номер 2024, С. 4 - 16

Опубликована: Март 3, 2024

With the escalation of cybercriminal activities, demand for forensic investigations into these crimeshas grown significantly. However, concept systematic pre-preparation potential forensicexaminations during software design phase, known as readiness, has only recently gainedattention. Against backdrop surging urban crime rates, this study aims to conduct a rigorous andprecise analysis and forecast rates in Los Angeles, employing advanced Artificial Intelligence(AI) technologies. This research amalgamates diverse datasets encompassing history, varioussocio-economic indicators, geographical locations attain comprehensive understanding howcrimes manifest within city. Leveraging sophisticated AI algorithms, focuses on scrutinizingsubtle periodic patterns uncovering relationships among collected datasets. Through thiscomprehensive analysis, endeavors pinpoint hotspots, detect fluctuations infrequency, identify underlying causes criminal activities. Furthermore, evaluates theefficacy model generating productive insights providing most accurate predictionsof future trends. These predictive are poised revolutionize strategies lawenforcement agencies, enabling them adopt proactive targeted approaches. Emphasizing ethicalconsiderations, ensures continued feasibility use while safeguarding individuals'constitutional rights, including privacy. The anticipated outcomes tofurnish actionable intelligence law enforcement, policymakers, planners, aiding theidentification effective prevention strategies. By harnessing AI, researchcontributes promotion data-driven models andprediction, offering promising avenue enhancing public security Angeles othermetropolitan areas.

Язык: Английский

---

Adversarial Attacks in Machine Learning: Key Insights and Defense Approaches

Applied Data Science and Analysis, Год журнала: 2024, Номер 2024, С. 121 - 147

Опубликована: Авг. 7, 2024

There is a considerable threat present in genres such as machine learning due to adversarial attacks which include purposely feeding the system with data that will alter decision region. These are committed presenting different models way model would be wrong its classification or prediction. The field of study still relatively young and has develop strong bodies scientific research eliminate gaps current knowledge. This paper provides literature review defenses based on highly cited articles conference published Scopus database. Through assessment 128 systematic articles: 80 original papers 48 till May 15, 2024, this categorizes reviews from domains, Graph Neural Networks, Deep Learning Models for IoT Systems, others. posits findings identified metrics, citation analysis, contributions these studies while suggesting area’s further development robustness’ protection mechanisms. objective work basic background defenses, need maintaining adaptability platforms. In context, contribute building efficient sustainable mechanisms AI applications various industries

Язык: Английский

---

Early Prediction of Cardiac Arrest in the Intensive Care Unit Using Explainable Machine Learning: Retrospective Study

Journal of Medical Internet Research, Год журнала: 2024, Номер 26, С. e62890 - e62890

Опубликована: Сен. 17, 2024

Background Cardiac arrest (CA) is one of the leading causes death among patients in intensive care unit (ICU). Although many CA prediction models with high sensitivity have been developed to anticipate CA, their practical application has challenging due a lack generalization and validation. Additionally, heterogeneity different ICU subtypes not adequately addressed. Objective This study aims propose clinically interpretable ensemble approach for timely accurate within 24 hours, regardless patient heterogeneity, including variations across populations subtypes. we conducted patient-independent evaluations emphasize model’s performance analyzed results that can be readily adopted by clinicians real-time. Methods Patients were retrospectively using data from Medical Information Mart Intensive Care-IV (MIMIC-IV) eICU-Collaborative Research Database (eICU-CRD). To address problem underperformance, constructed our framework feature sets based on vital signs, multiresolution statistical analysis, Gini index, 12-hour window capture unique characteristics CA. We extracted 3 types features each database compare between high-risk groups MIMIC-IV without eICU-CRD. After extraction, tabular network (TabNet) model screening cost-sensitive learning. assess real-time performance, used 10-fold leave-one-patient-out cross-validation cross–data set method. evaluated eICU-CRD cohort database. Finally, external validation databases was ability. The decision mask proposed method interpretability model. Results outperformed conventional approaches both it achieved higher accuracy than baseline various databases. enhance clinicians’ understanding serving as comparison non-CA groups. Next, tested trained eICU-CRD, respectively, evaluate demonstrated superior compared models. Conclusions Our novel learning provides stable predictive power environments. Most global information reveals differences groups, demonstrating its utility an indicator clinical decisions. Consequently, system validated algorithm enables intervene early applied trials digital health.

Язык: Английский

---

Prioritizing complex health levels beyond autism triage using fuzzy multi-criteria decision-making

Complex & Intelligent Systems, Год журнала: 2024, Номер 10(5), С. 6159 - 6188

Опубликована: Июнь 4, 2024

Abstract This study delves into the complex prioritization process for Autism Spectrum Disorder (ASD), focusing on triaged patients at three urgency levels. Establishing a dynamic solution is challenging resolving conflicts or trade-offs among ASD criteria. research employs fuzzy multi-criteria decision making (MCDM) theory across four methodological phases. In first phase, identifies dataset, considering 19 critical medical and sociodemographic criteria The second phase introduces new Decision Matrix (DM) designed to manage effectively. third focuses extension of Fuzzy-Weighted Zero-Inconsistency (FWZIC) construct weights using Single-Valued Neutrosophic 2-tuple Linguistic (SVN2TL). fourth formulates Multi-Attributive Border Approximation Area Comparison (MABAC) method rank within each level. Results from SVN2TL-FWZIC offer significant insights, including higher values "C12 = Laughing no reason" "C16 Notice sound bell" with 0.097358 0.083832, indicating their significance in identifying potential symptoms. base prioritizing triage levels MABAC, encompassing behavioral dimensions. methodology undergoes rigorous evaluation through sensitivity analysis scenarios, confirming consistency results points. compares benchmark studies, distinct points, achieves remarkable 100% congruence these prior investigations. implications this are far-reaching, offering valuable guide clinical psychologists cases patients.

Язык: Английский

---

Fuzzy Evaluation and Benchmarking Framework for Robust Machine Learning Model in Real-Time Autism Triage Applications

International Journal of Computational Intelligence Systems, Год журнала: 2024, Номер 17(1)

Опубликована: Июнь 17, 2024

Abstract In the context of autism spectrum disorder (ASD) triage, robustness machine learning (ML) models is a paramount concern. Ensuring ML faces issues such as model selection, criterion importance, trade-offs, and conflicts in evaluation benchmarking models. Furthermore, development must contend with two real-time scenarios: normal tests adversarial attack cases. This study addresses this challenge by integrating three key phases that bridge domains fuzzy multicriteria decision-making (MCDM). First, utilized dataset comprises authentic information, encompassing 19 medical sociodemographic features from 1296 autistic patients who received diagnoses via intelligent triage method. These were categorized into one labels: urgent, moderate, or minor. We employ principal component analysis (PCA) algorithms to fuse large number features. Second, fused forms basis for rigorously testing eight models, considering scenarios, evaluating classifier performance using nine metrics. The third phase developed robust framework encompasses creation decision matrix (DM) 2-tuple linguistic Fermatean opinion score method (2TLFFDOSM) multiple-ML perspectives, accomplished through individual external group aggregation ranks. Our findings highlight effectiveness PCA algorithms, yielding 12 components acceptable variance. ranking, logistic regression (LR) emerged top-performing terms 2TLFFDOSM (1.3370). A comparative five benchmark studies demonstrated superior our across all six checklist comparison points.

Язык: Английский

---

A novel dual-level multi-source information fusion approach for multicriteria decision making applications

Applied Intelligence, Год журнала: 2024, Номер 54(22), С. 11577 - 11602

Опубликована: Авг. 29, 2024

Язык: Английский

---

AI in the Field of Healthcare: A New Paradigm Examining Facilitators and Biases Through SEM-ANN

International Journal of Human-Computer Interaction, Год журнала: 2024, Номер unknown, С. 1 - 17

Опубликована: Июль 22, 2024

Язык: Английский

---