scholarly journals A Comprehensive Review of Intrusion Detection and Prevention Systems against Single Flood Attacks in SIP-Based Systems

2021 ◽  
Vol 13 (6) ◽  
pp. 13-25
Author(s):  
Sheeba. Armoogum ◽  
◽  
Nawaz. Mohamudally
Keyword(s):  
Comparative Analysis ◽  
Intrusion Detection ◽  
Detection Rate ◽  
Processing Time ◽  
Detection Rates ◽  
Voice Communication ◽  
Very Large Datasets ◽  
Novel Method ◽  
Effectiveness And Efficiency ◽  
Gap Models

Voice over Internet Protocol (VoIP) is a recent voice communication technology and due to its variety of calling capabilities, the system is expected to fuel the market value even further in the next five years. However, there are serious concerns since VoIP systems are frequently been attacked. According to recent security alliance reports, malicious activities have increased largely during the current pandemic against VoIP and other vulnerable networks. This hence implies that existing models are not sufficiently reliable since most of them do not have a hundred percent detection rate. In this paper, a review of our most recent Intrusion Detection & Prevention Systems (IDPS) developed is proposed together with a comparative analysis. The final work consisted of ten models which addressed flood intentional attacks to mitigate VoIP attacks. The methodological approaches of the studies included the quantitative and scientific paradigms, for which several instruments (comparative analysis and experiments) were used. Six prevention models were developed using three sorting methods combined with either a modified galloping algorithm or an extended quadratic algorithm. The seventh IDPS was designed by improving an existing genetic algorithm (e-GAP) and the eighth model is a novel deep learning method known as the Closest Adjacent Neighbour (CAN). Finally, for a better comparative analysis of AI-based algorithms, a Deep Analysis of the Intruder Tracing (DAIT) model using a bottom-up approach was developed to address the issues of processing time, effectiveness, and efficiency which were challenges when addressing very large datasets of incoming messages. This novel method prevented intruders to access a system without authorization and avoided any anomaly filtering at the firewall with a minimum processing time. Results revealed that the DAIT and the e-GAP models are very efficient and gave better results when benchmarking with models. These two models obtained an F-score of 98.83%, a detection rate of 100%, a false rate of 0%, an accuracy of 98.7%, and finally a processing time per message of 0.092 ms and 0.094 ms respectively. When comparing with previous models in the literature from which it is specified that detection rates obtained are 95.5% and falsepositive alarm of around 1.8%, except for one recent machine learning-based model having a detection rate of 100% and a processing time of 0.53 ms, the DAIT and the e-GAP models give better results.

scholarly journals Security Enrichment in Intrusion Detection System Using Classifier Ensemble

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Uma R. Salunkhe ◽  
Suresh N. Mali
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection Rate ◽  
Detection System ◽  
Hybrid Approach ◽  
Classifier Ensemble ◽  
Intrusion Detection Systems ◽  
Detection Rates ◽  
Detection Systems

In the era of Internet and with increasing number of people as its end users, a large number of attack categories are introduced daily. Hence, effective detection of various attacks with the help of Intrusion Detection Systems is an emerging trend in research these days. Existing studies show effectiveness of machine learning approaches in handling Intrusion Detection Systems. In this work, we aim to enhance detection rate of Intrusion Detection System by using machine learning technique. We propose a novel classifier ensemble based IDS that is constructed using hybrid approach which combines data level and feature level approach. Classifier ensembles combine the opinions of different experts and improve the intrusion detection rate. Experimental results show the improved detection rates of our system compared to reference technique.

scholarly journals Improving the Classification Effectiveness of Intrusion Detection by Using Improved Conditional Variational AutoEncoder and Deep Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2528 ◽  
Author(s):  
Yanqing Yang ◽  
Kangfeng Zheng ◽  
Chunhua Wu ◽  
Yixian Yang
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
False Positive ◽  
Detection Rate ◽  
Deep Neural Network ◽  
Training Data ◽  
Fine Tuning ◽  
Detection Methods ◽  
Detection Rates ◽  
Variational Autoencoder

Intrusion detection systems play an important role in preventing security threats and protecting networks from attacks. However, with the emergence of unknown attacks and imbalanced samples, traditional machine learning methods suffer from lower detection rates and higher false positive rates. We propose a novel intrusion detection model that combines an improved conditional variational AutoEncoder (ICVAE) with a deep neural network (DNN), namely ICVAE-DNN. ICVAE is used to learn and explore potential sparse representations between network data features and classes. The trained ICVAE decoder generates new attack samples according to the specified intrusion categories to balance the training data and increase the diversity of training samples, thereby improving the detection rate of the imbalanced attacks. The trained ICVAE encoder is not only used to automatically reduce data dimension, but also to initialize the weight of DNN hidden layers, so that DNN can easily achieve global optimization through back propagation and fine tuning. The NSL-KDD and UNSW-NB15 datasets are used to evaluate the performance of the ICVAE-DNN. The ICVAE-DNN is superior to the three well-known oversampling methods in data augmentation. Moreover, the ICVAE-DNN outperforms six well-known models in detection performance, and is more effective in detecting minority attacks and unknown attacks. In addition, the ICVAE-DNN also shows better overall accuracy, detection rate and false positive rate than the nine state-of-the-art intrusion detection methods.

scholarly journals Training: improving antenatal detection and outcomes of congenital heart disease

2018 ◽  
Vol 7 (4) ◽  
pp. e000276 ◽  
Author(s):  
Orhan Uzun ◽  
Julia Kennedy ◽  
Colin Davies ◽  
Anthony Goodwin ◽  
Nerys Thomas ◽  
...  
Keyword(s):  
Congenital Heart Disease ◽  
Detection Rate ◽  
Congenital Heart ◽  
Training Programme ◽  
Referral Rate ◽  
Cardiac Anomaly ◽  
Cardiac Ultrasound ◽  
Detection Rates ◽  
Antenatal Detection ◽  
The Uk

ObjectivesThis study describes the design, delivery and efficacy of a regional fetal cardiac ultrasound training programme. This programme aimed to improve the antenatal detection of congenital heart disease (CHD) and its effect on fetal and postnatal outcomes.Design setting and participantsThis was a prospective study that compared antenatal CHD detection rates by professionals from 13 hospitals in Wales before and after engaging in our ‘skills development programme’. Existing fetal cardiac practice and perinatal outcomes were continuously audited and progressive targets were set. The work was undertaken by the Welsh Fetal Cardiovascular Network, Antenatal Screening Wales (ASW), a superintendent sonographer and a fetal cardiologist.InterventionsA core professional network was established, engaging all stakeholders (including patients, health boards, specialist commissioners, ASW, ultrasonographers, radiologists, obstetricians, midwives and paediatricians). A cardiac educational lead (midwife, superintendent sonographer, radiologist, obstetrician, or a fetal medicine specialist) was established in each hospital. A new cardiac anomaly screening protocol (‘outflow tract view’) was created and training on the new protocol was systematically delivered at each centre. Data were prospectively collected and outcomes were continuously audited: locally by the lead fetal cardiologist; regionally by the Congenital Anomaly Register and Information Service in Wales; and nationally by the National Institute for Cardiac Outcomes and Research (NICOR) in the UK.Main outcome measuresPatient satisfaction; improvements in individual sonographer skills, confidence and competency; true positive referral rate; local hospital detection rate; national detection rate of CHD; clinical outcomes of selected cardiac abnormalities; reduction of geographical health inequality; cost efficacy.ResultsHigh levels of patient satisfaction were demonstrated and the professional skill mix in each centre was improved. The confidence and competency of sonographers was enhanced. Each centre demonstrated a reduction in the false-positive referral rate and a significant increase in cardiac anomaly detection rate. According to the latest NICOR data, since implementing the new training programme Wales has sustained its status as UK lead for CHD detection. Health outcomes of children with CHD have improved, especially in cases of transposition of the great arteries (for which no perinatal mortality has been reported since 2008). Standardised care led to reduction of geographical health inequalities with substantial cost saving to the National Health Service due to reduced false-positive referral rates. Our successful model has been adopted by other fetal anomaly screening programmes in the UK.ConclusionsAntenatal cardiac ultrasound mass training programmes can be delivered effectively with minimal impact on finite healthcare resources. Sustainably high CHD detection rates can only be achieved by empowering the regional screening workforce through continuous investment in lifelong learning activities. These should be underpinned by high quality service standards, effective care pathways, and robust clinical governance and audit practices.

Analysis of Feature Selection and Ensemble Classifier Methods for Intrusion Detection

2018 ◽  
Vol 7 (1) ◽  
pp. 57-72
Author(s):  
H.P. Vinutha ◽  
Poornima Basavaraju
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Detection Rate ◽  
Information Gain ◽  
False Positive Rate ◽  
Ensemble Classifier ◽  
Ensemble Classification ◽  
Chi Square ◽  
Traffic Pattern ◽  
Data Mining Algorithms

Day by day network security is becoming more challenging task. Intrusion detection systems (IDSs) are one of the methods used to monitor the network activities. Data mining algorithms play a major role in the field of IDS. NSL-KDD'99 dataset is used to study the network traffic pattern which helps us to identify possible attacks takes place on the network. The dataset contains 41 attributes and one class attribute categorized as normal, DoS, Probe, R2L and U2R. In proposed methodology, it is necessary to reduce the false positive rate and improve the detection rate by reducing the dimensionality of the dataset, use of all 41 attributes in detection technology is not good practices. Four different feature selection methods like Chi-Square, SU, Gain Ratio and Information Gain feature are used to evaluate the attributes and unimportant features are removed to reduce the dimension of the data. Ensemble classification techniques like Boosting, Bagging, Stacking and Voting are used to observe the detection rate separately with three base algorithms called Decision stump, J48 and Random forest.

scholarly journals Mortality due to primary brain tumours in China and detection rate in people with suspected symptoms: a nationally representative cross-sectional survey

2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Bin Jiang ◽  
Hongmei Liu ◽  
Dongling Sun ◽  
Haixin Sun ◽  
Xiaojuan Ru ◽  
...  
Keyword(s):  
Brain Tumour ◽  
Brain Tumours ◽  
Detection Rate ◽  
Epidemiological Data ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Detection Rates ◽  
Primary Brain Tumours ◽  
Symptom Screening ◽  
Nationally Representative

Abstract Background and purpose Epidemiological data on primary brain tumours (PBTs) are lacking due to the difficulty in case ascertainment among the population. Thus, we aimed to estimate mortality due to PBTs in China nationwide and the detection rate in people with suspected symptoms. Methods A multistage, complex sampling survey regarding mortality due to PBTs in Chinese individuals was carried out by reviewing all causes of death within a year. The detection rates in people with suspected symptoms were estimated based on PBT symptom screening and neurologist reviews and compared between groups by logistic regression analysis. Results Weighted mortality due to PBT was 1.6 (0.8–3.3) per 100,000 population in Chinese individuals, 1.8 (0.7–4.6) per 100,000 population in men, and 1.5 (0.5–4.5) per 100,000 population in women. Among 14,990 people with suspected symptoms, the PBT detection rate was 306.9 (95% CI 224.7–409.3) per 100,000 population in the total population, 233.0 (95% CI 135.7–373.1) per 100,000 population in men, and 376.9 (95% CI 252.4–546.3) per 100,000 population in women. People with an unsteady gait (OR 2.46; 95% CI 1.09–5.51; P=0.029), visual anomalies (3.84; 1.88–7.85; P<0.001), and headache (2.06; 1.10–3.86; P=0.023) were more likely to have a brain tumour than those without corresponding symptoms, while people with dizziness/vertigo were less likely to have a brain tumour than those without corresponding symptoms (0.45; 0.23–0.87; P=0.017). Conclusions Mortality due to PBT in China was low, with a nationwide estimate of 21,215 (10,427–43,165) deaths attributable to PBTs annually. However, the detection rate of PBTs can be greatly improved based on symptom screening in the population.

scholarly journals Security of Things Intrusion Detection System for Smart Healthcare

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1375
Author(s):  
Celestine Iwendi ◽  
Joseph Henry Anajemba ◽  
Cresantus Biamba ◽  
Desire Ngabo
Keyword(s):  
Genetic Algorithm ◽  
Intrusion Detection ◽  
False Alarm ◽  
False Alarm Rate ◽  
Detection Rate ◽  
Web Security ◽  
Intrusion Detection Systems ◽  
High Detection Rate ◽  
Detection Systems ◽  
Smart Healthcare

Web security plays a very crucial role in the Security of Things (SoT) paradigm for smart healthcare and will continue to be impactful in medical infrastructures in the near future. This paper addressed a key component of security-intrusion detection systems due to the number of web security attacks, which have increased dramatically in recent years in healthcare, as well as the privacy issues. Various intrusion-detection systems have been proposed in different works to detect cyber threats in smart healthcare and to identify network-based attacks and privacy violations. This study was carried out as a result of the limitations of the intrusion detection systems in responding to attacks and challenges and in implementing privacy control and attacks in the smart healthcare industry. The research proposed a machine learning support system that combined a Random Forest (RF) and a genetic algorithm: a feature optimization method that built new intrusion detection systems with a high detection rate and a more accurate false alarm rate. To optimize the functionality of our approach, a weighted genetic algorithm and RF were combined to generate the best subset of functionality that achieved a high detection rate and a low false alarm rate. This study used the NSL-KDD dataset to simultaneously classify RF, Naive Bayes (NB) and logistic regression classifiers for machine learning. The results confirmed the importance of optimizing functionality, which gave better results in terms of the false alarm rate, precision, detection rate, recall and F1 metrics. The combination of our genetic algorithm and RF models achieved a detection rate of 98.81% and a false alarm rate of 0.8%. This research raised awareness of privacy and authentication in the smart healthcare domain, wireless communications and privacy control and developed the necessary intelligent and efficient web system. Furthermore, the proposed algorithm was applied to examine the F1-score and precisionperformance as compared to the NSL-KDD and CSE-CIC-IDS2018 datasets using different scaling factors. The results showed that the proposed GA was greatly optimized, for which the average precision was optimized by 5.65% and the average F1-score by 8.2%.

scholarly journals The Effects of Social Distancing Policies on non-SARS-CoV-2 Respiratory Pathogens

2021 ◽  
Author(s):  
Jeff Nawrocki ◽  
Katherine Olin ◽  
Martin C Holdrege ◽  
Joel Hartsell ◽  
Lindsay Meyers ◽  
...  
Keyword(s):  
Public Health ◽  
Influenza A ◽  
Detection Rate ◽  
Respiratory Illness ◽  
Respiratory Pathogens ◽  
Public Health Response ◽  
Mixed Effect ◽  
Detection Rates ◽  
Social Distancing ◽  
The Impact

Abstract Background The initial focus of the US public health response to COVID-19 was the implementation of numerous social distancing policies. While COVID-19 was the impetus for imposing these policies, it is not the only respiratory disease affected by their implementation. This study aimed to assess the impact of social distancing policies on non-SARS-CoV-2 respiratory pathogens typically circulating across multiple US states. Methods Linear mixed-effect models were implemented to explore the effects of five social distancing policies on non-SARS-CoV-2 respiratory pathogens across nine states from January 1 through May 1, 2020. The observed 2020 pathogen detection rates were compared week-by-week to historical rates to determine when the detection rates were different. Results Model results indicate that several social distancing policies were associated with a reduction in total detection rate, by nearly 15%. Policies were associated with decreases in pathogen circulation of human rhinovirus/enterovirus and human metapneumovirus, as well as influenza A, which typically decrease after winter. Parainfluenza viruses failed to circulate at historical levels during the spring. Total detection rate in April 2020 was 35% less than historical average. Many of the pathogens driving this difference fell below historical detection rate ranges within two weeks of initial policy implementation. Conclusion This analysis investigated the effect of multiple social distancing policies implemented to reduce transmission of SARS-CoV-2 on non-SARS-CoV-2 respiratory pathogens. These findings suggest that social distancing policies may be used as an impactful public health tool to reduce communicable respiratory illness.

scholarly journals Comparison of colonoscopy after colonic diverticulitis and positive fecal immunochemical tests for the detection of colorectal neoplasia

2021 ◽  
Vol 09 (03) ◽  
pp. E331-E337
Author(s):  
Dai Nakamatsu ◽  
Tsutomu Nishida ◽  
Shinji Kuriki ◽  
Li-sa Chang ◽  
Kazuki Aochi ◽  
...  
Keyword(s):  
Detection Rate ◽  
Colorectal Neoplasia ◽  
Acute Diverticulitis ◽  
Colonic Diverticulitis ◽  
Detection Rates ◽  
Positive Group ◽  
Asymptomatic Patients ◽  
Polyp Detection Rate ◽  
Adenoma Detection ◽  
Acute Colonic Diverticulitis

Abstract Background and study aims The relationship between acute colonic diverticulitis and colorectal cancer (CRC) is unclear, but colonoscopy is recommended to exclude malignancy. We compared the detection rates for colorectal neoplasia in patients with colonic diverticulitis and asymptomatic patients who had positive fecal immunochemical tests (FITs). Patients and methods In total, 282 patients with acute colonic diverticulitis were hospitalized in our hospital from February 2011 to December 2019. Of them, 143 patients with diverticulitis and 1819 with positive FITs patients during the same period underwent colonoscopy without a prior colonoscopy within 5 years. We retrospectively compared these patients in terms of the invasive CRC rate, advanced neoplasia detection rate (ANDR), adenoma detection rate (ADR), and polyp detection rate (PDR). Results Compared to the diverticulitis group, the FIT-positive group had a significantly higher CRC rate (0 vs 2.7 %, P = 0.0061), ANDR (5.6 vs. 14.0 %, P = 0.0017), ADR (19.6 vs. 53.2 %, P < .0001), and PDR (44.1 vs. 91.0 %, P < .0001). Using 1:1 propensity score matching based on age and sex, we obtained 276 matched patients in both groups. After matching, no difference was found in the CRC rate (0 vs 0.7 %) or ANDR (5.8 vs 7.3 %) between groups, but the ADR and PDR were significantly higher in the FIT-positive group (20.3 vs 43.5 %, P < .0001; 45.7 % vs 86.2 %, P < .0001). Conclusion Patients with acute diverticulitis had lower ADRs and PDRs than patients with positive FITs.

Intrusion detection systems for RPL security: A comparative analysis

2021 ◽  
Vol 104 ◽  
pp. 102219
Author(s):  
George Simoglou ◽  
George Violettas ◽  
Sophia Petridou ◽  
Lefteris Mamatas
Keyword(s):  
Comparative Analysis ◽  
Intrusion Detection ◽  
Intrusion Detection Systems ◽  
Detection Systems
Sign in / Sign up

Export Citation Format

Share Document