Data Sanitization to Reduce Private Information Leakage from Functional Genomics.

The generation of functional genomics datasets is surging, because they provide insight into gene regulation and organismal phenotypes (e.g., genes upregulated in cancer). The intent behind functional genomics experiments is not necessarily to study genetic variants, yet they pose privacy concerns due to their use of next-generation sequencing. Moreover, there is a great incentive to broadly share raw reads for better statistical power and general research reproducibility. Thus, we need new modes of sharing beyond traditional controlled-access models. Here, we develop a data-sanitization procedure allowing raw functional genomics reads to be shared while minimizing privacy leakage, enabling principled privacy-utility trade-offs. Our protocol works with traditional Illumina-based assays and newer technologies such as 10x single-cell RNA sequencing. It involves quantifying the privacy leakage in reads by statistically linking study participants to known individuals. We carried out these linkages using data from highly accurate reference genomes and more realistic environmental samples.

Cancer risk among World Trade Center rescue and recovery workers: A review.

Twenty years after the September 11th, 2001 terrorist attacks, the association between exposures present at the World Trade Center (WTC) site and the risk of several specific types of cancer has been reported among rescue and recovery workers. The authors' objective was to conduct an updated review of these data. Most studies have found elevated rates of both prostate and thyroid cancers compared with rates in the general population, and some have reported statistically significant differences for the rates of all cancers as well. Studies including a larger combined cohort of WTC-exposed rescue and recovery workers from 3 main cohorts have since replicated findings for these cancers, with additional years of follow-up. Among this combined cohort, although a lower-than-expected standardized incidence ratio for all cancers was observed, WTC exposure was also related to an increased risk of cutaneous melanoma and tonsil cancer. Importantly, another study found that WTC-exposed rescue and recovery workers who are enrolled in the federally funded medical monitoring and treatment program experienced improved survival post-cancer diagnosis compared with New York state patients with cancer. On the basis of these combined cohort studies, the full effect of WTC exposure on cancer risk is becoming clearer. Consequently, the authors believe that surveillance of those with WTC exposure should be continued, and in-depth analysis of epidemiologic, molecular, and clinical aspects of specific cancers in these workers should be pursued.

Low rate hippocampal delay period activity encodes behavioral experience.

Remembering what just happened is a crucial prerequisite to form long-term memories but also for establishing and maintaining working memory. So far there is no general agreement about cortical mechanisms that support short-term memory. Using a classifier-based decoding approach, we report that hippocampal activity during few sparsely distributed brief time intervals contains information about the previous sensory motor experience of rodents. These intervals are characterized by only a small increase of firing rate of only a few neurons. These low-rate predictive patterns are present in both working memory and non-working memory tasks, in two rodent species, rats and Mongolian gerbils, are strongly reduced for rats with medial entorhinal cortex lesions, and depend on the familiarity of the sensory-motor context.

Panicolytic-like effects of environment enrichment on male mice threatened by Bothrops jararaca lancehead pit vipers.

Environment enrichment (EE) is a well-known eustress model showing beneficial effects in different psychiatric diseases, but its positive properties in panic disorders are not yet established. The confrontation between prey and predator in complex arenas has been validated as a putative panic attack model. The principal aim of this work was to investigate the role of the EE on panic-like defensive responses elicited by mice threatened by venomous snakes. After 6 weeks of exposure either to an enriched or standard environments, 36 male mice were habituated in a complex polygonal arena for snakes containing an artificial burrow and elevated platforms for escape. The animals were confronted by Bothrops jararaca for 5 min, and the following antipredatory responses were recorded: defensive attention, stretched attend posture, flat back approach, prey versus predator interaction, oriented escape behavior, time spent in a safe place, and number of crossings. Mice threatened by snakes displayed several antipredatory reactions as compared to the exploratory behavior of those animals submitted to a nonthreatening situation (toy snake) in the same environment. Notably, EE causes anxiolytic- and panicolytic-like effects significantly decreasing the defensive attention and time spent in safe places and significantly increasing both prey versus predator interaction and exploratory behavior. In conclusion, our data demonstrate that EE can alter the processing of fear modulation regarding both anxiety- and panic-like responses in a dangerous condition, significantly modifying the decision-making defensive strategy.

Digital DNA lifecycle security and privacy: an overview.

DNA sequencing technologies have advanced significantly in the last few years leading to advancements in biomedical research which has improved personalised medicine and the discovery of new treatments for diseases. Sequencing technology advancement has also reduced the cost of DNA sequencing, which has led to the rise of direct-to-consumer (DTC) sequencing, e.g. 23andme.com, ancestry.co.uk, etc. In the meantime, concerns have emerged over privacy and security in collecting, handling, analysing and sharing DNA and genomic data. DNA data are unique and can be used to identify individuals. Moreover, those data provide information on people's current disease status and disposition, e.g. mental health or susceptibility for developing cancer. DNA privacy violation does not only affect the owner but also affects their close consanguinity due to its hereditary nature. This article introduces and defines the term 'digital DNA life cycle' and presents an overview of privacy and security threats and their mitigation techniques for predigital DNA and throughout the digital DNA life cycle. It covers DNA sequencing hardware, software and DNA sequence pipeline in addition to common privacy attacks and their countermeasures when DNA digital data are stored, queried or shared. Likewise, the article examines DTC genomic sequencing privacy and security.

Ecosystem services at risk from disturbance in Europe's forests.

Global change impacts on disturbances can strongly compromise the capacity of forests to provide ecosystem services to society. In addition, many ecosystem services in Europe are simultaneously provided by forests, emphasizing the importance of multifunctionality in forest ecosystem assessments. To address disturbances in forest ecosystem policies and management, spatially explicit risk analyses that consider multiple disturbances and ecosystem services are needed. However, we do not yet know which ecosystem services are most at risk from disturbances in Europe, where the respective risk hotspots are, nor which of the main disturbance agents are most detrimental to the provisioning of multiple ecosystem services from Europe's forests. Here, we quantify the risk of losing important ecosystem services (timber supply, carbon storage, soil erosion control and outdoor recreation) to forest disturbances (windthrows, bark beetle outbreaks and wildfires) in Europe on a continental scale. We find that up to 12% of Europe's ecosystem service supply is at risk from current disturbances. Soil erosion control is the ecosystem service at the highest risk, and windthrow is the disturbance agent posing the highest risk. Disturbances challenge forest multifunctionality by threatening multiple ecosystem services simultaneously on 19.8 Mha (9.7%) of Europe's forests. Our results highlight priority areas for risk management aiming to safeguard the sustainable provisioning of forest ecosystem services.

Patient-level indirect treatment comparison of lanadelumab versus pdC1-INH i.v. in hereditary angioedema patients: PATCH study.

BACKGROUND: Hereditary angioedema (HAE) is an autosomal dominant inherited disease in which patients suffer from local attacks primarily affecting skin and gastrointestinal tract, and sometimes even the upper respiratory tract leading to asphyxiation. Since head-to-head trials between authorized treatments are lacking, this study compares efficacy and safety of lanadelumab and intravenous plasma-derived C1-esterase inhibitor (pdC1-INH i.v.) in HAE patients on long-term prophylaxis by means of an indirect treatment comparison. METHODS: Efficacy and safety of lanadelumab against pdC1-INH i.v. were analyzed in a fully prespecified indirect comparison based on individual patient data (n = 231) from the HELP and CHANGE clinical trials. Primary and secondary efficacy endpoints were compared using a generalized linear model for count data. Confounding variables were identified a priori via systematic literature research and validated by clinical experts. Adjustment of confounders was implemented using a conditional regression model. RESULTS: Lanadelumab showed a statistically significant improvement in reduction of HAE attack rates compared to pdC1-INH i.v. across multiple endpoints: Monthly attack rate of patients treated with lanadelumab was less than half compared to pdC1-INH i.v. (Rate ratio: 0.486; 95% CI: 0.253, 0.932). Monthly rate of laryngeal attacks was found to be five times lower for lanadelumab (Rate ratio: 0.2; 95% CI: 0.044, 0.915) and monthly rate of acute treated HAE attacks among lanadelumab patients was about one third of the attack rate of pdC1-INH i.v. patients (Rate ratio: 0.366; 95% CI: 0.185, 0.727). CONCLUSION: This study contributes to current knowledge in the treatment of HAE by indicating a statistically significant reduction of HAE attacks under lanadelumab compared to pdC1-INH i.v.

SUNCT, SUNA and short-lasting unilateral neuralgiform headache attacks: Debates and an update.

BACKGROUND: Short-lasting unilateral neuralgiform headache attacks (SUNHA) have the features of both short-lasting unilateral neuralgiform pain, such as trigeminal neuralgia or stabbing headache, and associated trigeminal autonomic symptoms, such as paroxysmal hemicrania or cluster headache. Recognizing and adequately treating SUNHA is essential but current treatment methods are ineffective in treating SUNHA. METHODS: We reviewed the changes in the concept of short-lasting unilateral neuralgiform headache attacks and provide a narrative review of the current medical and surgical treatment options, from the first choice of treatment for patients to treatments for selective intractable cases. RESULTS: Unlike the initial impression of an intractable primary headache disorder affecting older men, SUNHA affects both sexes throughout their lifespan. One striking feature of SUNHA is that the attacks are triggered by cutaneous or intraoral stimulation. The efficacy of conventional treatments is disappointing and challenging, and preventive therapy is the mainstay of treatment because of highly frequent attacks of a very brief duration. Amongst them, lamotrigine is effective in approximately two-third of the patients with SUNHA, and intravenous lidocaine is essential for the management of acute exacerbation of intractable pain. Topiramate, oxcarbazepine and gabapentin are considered good secondary options for SUNHA, and botulinum toxin can be used in selective cases. Neurovascular compression is commonly observed in SUNHA, and surgical approaches, such as neurovascular compression, have been reported to be effective for intractable cases. CONCLUSIONS: Recent advances in the understanding of SUNHA have improved the recognition and treatment approaches for this unique condition.

Case-based discussion of the acute hepatic porphyrias: Updates on pathogenesis, diagnosis and management.

The acute hepatic porphyrias (AHPs) include three autosomal dominant disorders, acute intermittent porphyria, variegate porphyria  and hereditary coproporphyria, and the ultra-rare autosomal recessive 5-aminolevulinic acid dehydratase-deficient porphyria. All four are characterized by episodic acute neurovisceral attacks that can be life-threatening if left untreated. The attacks are precipitated by factors that induce hepatic 5-aminolevulinic acid synthase 1 (ALAS1), resulting in accumulation of the porphyrin precursors, 5-aminolevulinic acid and porphobilinogen, which are believed to cause neurotoxicity. Diagnosis of these rare disorders is often delayed because the symptoms are non-specific with many common aetiologies. However, once clinical suspicion of an AHP is raised, diagnosis can be made by specialized biochemical testing, particularly during attacks. Moderate or severe attacks are treated with intravenous hemin infusions, together with supportive care to relieve pain and other symptoms. Prophylactic treatments are recommended in patients with confirmed recurrent attacks (≥4 attacks in a maximum period of 12 months), the most effective being givosiran, an RNAi therapeutic targeting hepatocyte ALAS1 mRNA. AHP patients with clinically and/or biochemically active disease are at elevated risk for developing long-term complications, including chronic kidney disease, chronic hypertension and hepatocellular carcinoma, thus, surveillance is recommended. Here, using a case-based format, we provide an update on the pathogenesis, diagnosis and treatment of the AHPs based on literature review and clinical experiences.

Restless sleep disorder in children with epileptic and non-epileptic nocturnal attacks.

Restless sleep disorder (RSD) is an important sleep disorder characterised by the presence of frequent large muscle movements (LMM) during sleep, which may be comorbid to other conditions/diseases. In this study, we investigated the frequency and the characteristics of RSD among children who were evaluated by polysomnography (PSG) due to epileptic and non-epileptic nocturnal attacks. We analysed consecutively children younger than 18 years who were referred for PSG recording due to abnormal motor activities during sleep. The diagnosis of nocturnal events as sleep-related epilepsy was made based on the current consensus. Patients who were referred with suspicion of sleep-related epilepsy, but who were diagnosed to have non-epileptic nocturnal events and children with a definitive diagnosis of NREM sleep parasomnias were also enrolled. Sixty-two children were analysed in this study (17 children with sleep-related epilepsy, 20 children with NREM parasomnia, and 25 children with nocturnal events not otherwise classified [neNOS]). The mean number of LMM, LMM index, LMM-associated with arousal and its index were all significantly higher in children with sleep-related epilepsy. Restless sleep disorder was present in 47.1% of patients with epilepsy, 25% of patients with parasomnia, and in 20% of patients with neNOS. The mean A3 duration and the A3 index were higher in children with sleep-related epilepsy and RSD compared with those with parasomnia and restless sleep disorder. Patients with RSD had lower ferritin levels than those without RSD in all subgroups. Our study demonstrates a high prevalence of restless sleep disorder in children with sleep-related epilepsy, associated with an increased cyclic alternating pattern.

The impact of fear of attacks on pain-related disability in cluster headache: Insights from the fear avoidance model.

OBJECTIVE: This study utilized the theoretical framework of the "fear avoidance model" (FAM) and investigated the role of fear of attack in pain-related disability. To this end, a measurement specific to cluster headache (CH) was used to investigate whether fear of attacks, alongside attack frequency, is a significant predictor of pain-related disability in CH. BACKGROUND: Cluster headache substantially impacts daily functioning, yet empirical research exploring specific contributing factors is limited. METHODS: A cross-sectional online survey was undertaken in patients with CH, gathering sociodemographic, clinical data, and responses on the Cluster Headache Scale and the Depression, Anxiety and Stress Scale. RESULTS: Analysis of data from 640 patients (chronic CH: 287/640 [44.8%]; female: 264/640 [41.3%]; male: 373/640 [58.3%]; gender diverse: three of 640 [0.5%]; age range: 18-86 years; mean [standard deviation] Cluster Headache Scales subscale disability score: 36.9 [9.8]; out of 869 respondents) revealed that both attack frequency and fear of attacks significantly predicted pain-related disability (p < 0.001, percentage of variance explained: R2 = 0.24). More variance was explained by fear of attacks (R2 = 0.22) than by attack frequency (R2 = 0.02). This relationship remained significant even when controlling for depression and anxiety, which were also identified as independent predictors of pain-related disability (p < 0.001, R2 = 0.44). CONCLUSION: This study emphasizes the relevance of psychological factors in CH-related disability. Fear of attacks was found to be an independent predictor, while attack frequency was of minor relevance. Empirical investigation of the FAM in CH could improve the understanding of the mechanisms underlying disability and contribute to the development of CH-specific interventions.

Course of Duration and Trigger Factors of Vertigo Attacks in Patients with Benign Recurrent Vertigo, Menière's Disease, or Vestibular Migraine.

INTRODUCTION: Benign recurrent vertigo (BRV), Menière's disease (MD), and vestibular migraine (VM) show many similarities with regard to the course of vertigo attacks and clinical features. In this paper, we elaborate on the decreasing frequency of vertigo attacks observed in a previous study from our group by exploring changes in the duration and trigger factors of vertigo attacks in patients with BRV, MD, or VM. METHODS: For this 3-year prospective cohort study in our tertiary referral center we recruited patients with a confirmed diagnosis of BRV, MD, or VM by a neurologist and otorhinolaryngologist in our center in 2015-2016. A study-specific questionnaire was used to assess the usual duration of vertigo attacks and their potential triggers every 6 months. Main outcome measures were changes in duration and trigger factors of vertigo attacks in the subgroups of patients with persisting attacks, which were analyzed using repeated measures logistic regression models. RESULTS: 121 patients were included (BRV: n = 44; MD: n = 43; VM: n = 34) of whom 117 completed the 3-year follow-up period and 57 (48.7%) kept reporting vertigo attacks at one more follow-up measurements. None of the diagnosis groups showed statistically significant shortening of attack duration at the subsequent annual follow-up measurements compared to baseline. At baseline, stress and fatigue being reported as triggers for attacks differed significantly between the three groups (stress: BRV 40.9%, MD 62.8%, VM 76.5%, p = 0.005; fatigue: BRV 31.0%, MD 48.8%, VM 68.8%, p = 0.003). In the VM group, a consistent reduction of stress and fatigue as triggers was observed up until the 24- and the 30-month follow-up measurements, respectively, with odds ratios (ORs) ranging from 0.15 to 0.33 (all p < 0.05). In the MD group, a consistent reduction of head movements as trigger was observed from the 24-month measurement onward (ORs ranging from 0.07 to 0.11, all p < 0.05). CONCLUSION: Our study showed no reduction in vertigo attack duration over time in patients with BRV, MD, and VM who remain to have vertigo attacks. In VM and MD patients with persisting vertigo attacks stress, fatigue and head movements became less predominant triggers for vertigo attacks.

Multi-level authentication for security in cloud using improved quantum key distribution.

Cloud computing is an on-demand virtual-based technology to develop, configure, and modify applications online through the internet. It enables the users to handle various operations such as storage, back-up, and recovery of data, data analysis, delivery of software applications, implementation of new services and applications, hosting websites and blogs, and streaming of audio and video files. Thereby, it provides us many benefits although it is backlashed due to problems related to cloud security like data leakage, data loss, cyber attacks, etc. To address the security concerns, researchers have developed a variety of authentication mechanisms. This means that the authentication procedure used in the suggested method is multi-levelled. As a result, a better QKD method is offered to strengthen cloud security against different types of security risks. Key generation for enhanced QKD is based on the ABE public key cryptography approach. Here, an approach named CPABE is used in improved QKD. The Improved QKD scored the reduced KCA attack ratings of 0.3193, this is superior to CMMLA (0.7915), CPABE (0.8916), AES (0.5277), Blowfish (0.6144), and ECC (0.4287), accordingly. Finally, this multi-level authentication using an improved QKD approach is analysed under various measures and validates the enhancement over the state-of-the-art models.

Enhancement of cyber security in IoT based on ant colony optimized artificial neural adaptive Tensor flow.

The Internet of Things (IoT) is a network that connects various hardware, software, data storage, and applications. These interconnected devices provide services to businesses and can potentially serve as entry points for cyber-attacks. The privacy of IoT devices is increasingly vulnerable, particularly to threats like viruses and illegal software distribution lead to the theft of critical information. Ant Colony-Optimized Artificial Neural-Adaptive Tensorflow (ACO-ANT) technique is proposed to detect malicious software illicitly disseminated through the IoT. To emphasize the significance of each token in source duplicate data, the noise data undergoes processing using tokenization and weighted attribute techniques. Deep learning (DL) methods are then employed to identify source code duplication. Also the Multi-Objective Recurrent Neural Network (M-RNN) is used to identify suspicious activities within an IoT environment. The performance of proposed technique is examined using Loss, accuracy, F measure, precision to identify its efficiency. The experimental outcomes demonstrate that the proposed method ACO-ANT on Malimg dataset provides 12.35%, 14.75%, 11.84% higher precision and 10.95%, 15.78%, 13.89% higher f-measure compared to the existing methods. Further, leveraging block chain for malware detection is a promising direction for future research the fact that could enhance the security of IoT and identify malware threats.

Adaptive activation Functions with Deep Kronecker Neural Network optimized with Bear Smell Search Algorithm for preventing MANET Cyber security attacks.

An Adaptive activation Functions with Deep Kronecker Neural Network optimized with Bear Smell Search Algorithm (BSSA) (ADKNN-BSSA-CSMANET) is proposed for preventing MANET Cyber security attacks. The mobile users are enrolled with Trusted Authority Using a Crypto Hash Signature (SHA-256). Every mobile user uploads their finger vein biometric, user ID, latitude and longitude for confirmation. The packet analyser checks if any attack patterns are identified. It is implemented using adaptive density-based spatial clustering (ADSC) that deems information from packet header. Geodesic filtering (GF) is used as a pre-processing method for eradicating the unsolicited content and filtering pertinent data. Group Teaching Algorithm (GTA)-based feature selection is utilized for ideal collection of features and Adaptive Activation Functions along Deep Kronecker Neural Network (ADKNN) is used to categorizing normal and attack packets (DoS, Probe, U2R, and R2L). Then BSSA is utilized for optimizing the weight parameters of ADKNN classifier for optimal classification. The proposed technique is executed in python and its efficiency is evaluated by several performances metrics, such as Accuracy, Attack Detection Rate, Detection Delay, Packet Delivery Ratio, Throughput, and Energy Consumption. The proposed technique provides 36.64%, 33.06%, and 33.98% lower Detection Delay on NSL-KDD dataset compared with the existing methods.

Psychological distress and uterine fibroids: a bidirectional two-sample mendelian randomization study.

BACKGROUND: Observational data indicates a connection between emotional discomfort, such as anxiety and depression, and uterine fibroids (UFs). However, additional investigation is required to establish the causal relationship between them. Hence, we assessed the reciprocal causality between four psychological disorders and UFs utilizing two-sample Mendelian randomization (MR). METHODS: To evaluate the causal relationship between four types of psychological distress (depressive symptoms, severe depression, anxiety or panic attacks, mood swings) and UFs, bidirectional two-sample MR was employed, utilizing single nucleotide polymorphisms (SNPs) associated with these conditions. Both univariate MR (UVMR) and multivariate MR (MVMR) primarily applied inverse variance weighted (IVW) as the method for estimating potential causal effects. Complementary approaches such as MR Egger, weighted median, simple mode, and weighted mode were utilized to validate the findings. To assess the robustness of our MR results, we conducted sensitivity analyses using Cochran's Q-test and the MR Egger intercept test. RESULTS: The results of our UVMR analysis suggest that genetic predispositions to depressive symptoms (Odds Ratio [OR] = 1.563, 95% Confidence Interval [CI] = 1.209-2.021, P = 0.001) and major depressive disorder (MDD) (OR = 1.176, 95% CI = 1.044-1.324, P = 0.007) are associated with an increased risk of UFs. Moreover, the IVW model showed a nominally significant positive correlation between mood swings (OR: 1.578; 95% CI: 1.062-2.345; P = 0.024) and UFs risk. However, our analysis did not establish a causal relationship between UFs and the four types of psychological distress. Even after adjusting for confounders like body mass index (BMI), smoking, alcohol consumption, and number of live births in the MVMR, the causal link between MDD and UFs remained significant (OR = 1.217, 95% CI = 1.039-1.425, P = 0.015). CONCLUSIONS: Our study presents evidence supporting the causal relationship between genetic susceptibility to MDD and the incidence of UFs. These findings highlight the significance of addressing psychological health issues, particularly depression, in both the prevention and treatment of UFs.

Quantitative assessment of machine learning reliability and resilience.

Advances in machine learning (ML) have led to applications in safety-critical domains, including security, defense, and healthcare. These ML models are confronted with dynamically changing and actively hostile conditions characteristic of real-world applications, requiring systems incorporating ML to be reliable and resilient. Many studies propose techniques to improve the robustness of ML algorithms. However, fewer consider quantitative techniques to assess changes in the reliability and resilience of these systems over time. To address this gap, this study demonstrates how to collect relevant data during the training and testing of ML suitable for the application of software reliability, with and without covariates, and resilience models and the subsequent interpretation of these analyses. The proposed approach promotes quantitative risk assessment of ML technologies, providing the ability to track and predict degradation and improvement in the ML model performance and assisting ML and system engineers with an objective approach to compare the relative effectiveness of alternative training and testing methods. The approach is illustrated in the context of an image recognition model, which is subjected to two generative adversarial attacks and then iteratively retrained to improve the system's performance. Our results indicate that software reliability models incorporating covariates characterized the misclassification discovery process more accurately than models without covariates. Moreover, the resilience model based on multiple linear regression incorporating interactions between covariates tracks and predicts degradation and recovery of performance best. Thus, software reliability and resilience models offer rigorous quantitative assurance methods for ML-enabled systems and processes.

Systematic Literature Review of IoT Botnet DDOS Attacks and Evaluation of Detection Techniques.

Internet of Things (IoT) technology has become an inevitable part of our daily lives. With the increase in usage of IoT Devices, manufacturers continuously develop IoT technology. However, the security of IoT devices is left behind in those developments due to cost, size, and computational power limitations. Since these IoT devices are connected to the Internet and have low security levels, one of the main risks of these devices is being compromised by malicious malware and becoming part of IoT botnets. IoT botnets are used for launching different types of large-scale attacks including Distributed Denial-of-Service (DDoS) attacks. These attacks are continuously evolving, and researchers have conducted numerous analyses and studies in this area to narrow security vulnerabilities. This paper systematically reviews the prominent literature on IoT botnet DDoS attacks and detection techniques. Architecture IoT botnet DDoS attacks, evaluations of those attacks, and systematically categorized detection techniques are discussed in detail. The paper presents current threats and detection techniques, and some open research questions are recommended for future studies in this field.

Sybil Attacks Detection and Traceability Mechanism Based on Beacon Packets in Connected Automobile Vehicles.

Connected Automobile Vehicles (CAVs) enable cooperative driving and traffic management by sharing traffic information between them and other vehicles and infrastructures. However, malicious vehicles create Sybil vehicles by forging multiple identities and sharing false location information with CAVs, misleading their decisions and behaviors. The existing work on defending against Sybil attacks has almost exclusively focused on detecting Sybil vehicles, ignoring the traceability of malicious vehicles. As a result, they cannot fundamentally alleviate Sybil attacks. In this work, we focus on tracking the attack source of malicious vehicles by using a novel detection mechanism that relies on vehicle broadcast beacon packets. Firstly, the roadside units (RSUs) randomly instruct vehicles to perform customized key broadcasting and listening within communication range. This allows the vehicle to prove its physical presence by broadcasting. Then, RSU analyzes the beacon packets listened to by the vehicle and constructs a neighbor graph between the vehicles based on the customized particular fields in the beacon packets. Finally, the vehicle's credibility is determined by calculating the edge success probability of vehicles in the neighbor graph, ultimately achieving the detection of Sybil vehicles and tracing malicious vehicles. The experimental results demonstrate that our scheme achieves the real-time detection and tracking of Sybil vehicles, with precision and recall rates of 98.53% and 95.93%, respectively, solving the challenge of existing detection schemes failing to combat Sybil attacks from the root.

Proactive Threat Hunting in Critical Infrastructure Protection through Hybrid Machine Learning Algorithm Application.

Cyber-security challenges are growing globally and are specifically targeting critical infrastructure. Conventional countermeasure practices are insufficient to provide proactive threat hunting. In this study, random forest (RF), support vector machine (SVM), multi-layer perceptron (MLP), AdaBoost, and hybrid models were applied for proactive threat hunting. By automating detection, the hybrid machine learning-based method improves threat hunting and frees up time to concentrate on high-risk warnings. These models are implemented on approach devices, access, and principal servers. The efficacy of several models, including hybrid approaches, is assessed. The findings of these studies are that the AdaBoost model provides the highest efficiency, with a 0.98 ROC area and 95.7% accuracy, detecting 146 threats with 29 false positives. Similarly, the random forest model achieved a 0.98 area under the ROC curve and a 95% overall accuracy, accurately identifying 132 threats and reducing false positives to 31. The hybrid model exhibited promise with a 0.89 ROC area and 94.9% accuracy, though it requires further refinement to lower its false positive rate. This research emphasizes the role of machine learning in improving cyber-security, particularly for critical infrastructure. Advanced ML techniques enhance threat detection and response times, and their continuous learning ability ensures adaptability to new threats.