1. |
- Ahmed, Mumtahina, et al.
(author)
-
Explainable Text Classification Model for COVID-19 Fake News Detection
- 2022
-
In: Journal of Internet Services and Information Security (JISIS). - : Innovative Information Science & Technology Research Group. - 2182-2069 .- 2182-2077. ; 12:2, s. 51-69
-
Journal article (peer-reviewed)abstract
- Artificial intelligence has achieved notable advances across many applications, and the field is recently concerned with developing novel methods to explain machine learning models. Deep neural networks deliver the best performance accuracy in different domains, such as text categorization, image classification, and speech recognition. Since the neural network models are black-box types, they lack transparency and explainability in predicting results. During the COVID-19 pandemic, Fake News Detection is a challenging research problem as it endangers the lives of many online users by providing misinformation. Therefore, the transparency and explainability of COVID-19 fake news classification are necessary for building the trustworthiness of model prediction. We proposed an integrated LIME-BiLSTM model where BiLSTM assures classification accuracy, and LIME ensures transparency and explainability. In this integrated model, since LIME behaves similarly to the original model and explains the prediction, the proposed model becomes comprehensible. The performance of this model in terms of explainability is measured by using Kendall’s tau correlation coefficient. We also employ several machine learning models and provide a comparison of their performances. Therefore, we analyzed and compared the computation overhead of our proposed model with the other methods because the model takes the integrated strategy.
|
|
2. |
- Alizadeh, Morteza, 1987-, et al.
(author)
-
A Survey of Secure Internet of Things in Relation to Blockchain
- 2020
-
In: Journal of Internet Services and Information Security (JISIS). - Seoul, Republic of Korea : Innovative Information Science & Technology Research Group (ISYOU). - 2182-2069 .- 2182-2077. ; 10:3, s. 47-75
-
Journal article (peer-reviewed)abstract
- Distributed ledgers and blockchain technologies can improve system security and trustworthiness by providing immutable replicated histories of data. Blockchain is a linked list of blocks containing digitally signed transactions, a cryptographic hash of the previous block, and a timestamp stored in a decentralized and distributed network. The Internet of Things (IoT) is one of the application domains in which security based on blockchain is discussed. In this article, we review the structure and architectures of distributed IoT systems and explain the motivations, challenges, and needs of blockchain to secure such systems. However, there are substantial threats and attacks to blockchain that must be understood, as well as suitable approaches to mitigate them. We, therefore, survey the most common attacks to blockchain systems and the solutions to mitigate them, with the objective of assessing how malicious these attacks are in the IoT context.
|
|
3. |
- Andersson, Karl
(author)
-
Interworking techniques and architectures for heterogeneous wireless networks
- 2012
-
In: Journal of Internet Services and Information Security (JISIS). - 2182-2069 .- 2182-2077. ; 2:1/2, s. 22-48
-
Journal article (peer-reviewed)abstract
- Fourth generation (4G) wireless systems targeting 100 Mb/s for highly mobile scenarios and 1 Gb/s for low mobility communication are soon to be deployed on a broad basis with LTE-Advanced and IEEE 802.16m as the two candidate systems. Traditional applications spanning everything from voice, video, and data to new machine-to-machine (M2M) applications with billions of connected devices transmitting sensor data will in a soon future use these networks. Still, interworking solutions integrating those new 4G networks with existing legacy wireless networks are important building blocks in order to achieve cost-efficient solutions, offer smooth migration paths from legacy systems, and to provide means for load balancing among different radio access technologies.This article categorizes and analyzes different interworking solutions for heterogeneous wireless networks and provides suggestions for further research.
|
|
4. |
- Arfizurrahmanl, Mohammad, et al.
(author)
-
Real-time non-intrusive driver fatigue detection system using belief rule-based expert system
- 2021
-
In: Journal of Internet Services and Information Security (JISIS). - : Innovative Information Science and Technology Research Group. - 2182-2069 .- 2182-2077. ; 11:4, s. 44-60
-
Journal article (peer-reviewed)abstract
- This paper presents a non-intrusive system for detecting driver fatigue in real-time. To determine the level of fatigue the system uses various visual features, namely head nodding, eye closure duration and yawning. A state-of-the-art facial landmark detector âIntraFaceâ has been adopted to determine the eye state, mouth state and head pose estimation. However, different forms of uncertainties such as vagueness, imprecision, ambiguity and incompleteness are involved in calculating these visual parameters. Therefore, a Belief Rule-Based Expert System (BRBES) is employed, which has the ability to handle the uncertainties. The information of the visual parameters is sent to BRBES as input to determine the level of fatigue. An optimal learning model has been developed to improve the performance and accuracy of the BRBES. A comparison between the system and the fuzzy rulebased expert system has been carried out. The system generates more effective and reliable results than the fuzzy rule-based expert system.
|
|
5. |
- Booth, Todd, et al.
(author)
-
Network Security of Internet Services: Eliminate DDoS Reflection Amplification Attacks
- 2015
-
In: Journal of Internet Services and Information Security (JISIS). - 2182-2069 .- 2182-2077. ; 5:3, s. 58-79
-
Journal article (peer-reviewed)abstract
- Our research problem is that there are a large number of successful network reflection DDoS attacks. Via a UDP Reflection Attack, an attacker can send just 1 Gb/s of payload to innocent servers, and it is these servers which then can send over 4,600 times the payload to the victim! There are very expensive and complex solutions in use today, however most all of these on premise solutions can be easily circumvented. The academic community has not adequately addressed this research problem. We have created a new Internet services network security surface attack mitigation methodology. Our novel design patterns will help organizations improve the price/performance of their anti-network reflection solution by 100 times, as compared to common on premise solutions. Our analysis and results confirm that our solution is viable. Our novel solution is based on stateless IP packet header filtering firewalls (which can be implemented mostly in hardware due to their simplicity). We have reduced and in some cases eliminated the need for researchers to even try and find new ways to filter the same traffic via more complex, software driven stateful solutions.
|
|
6. |
- Brunetta, Carlo, 1992, et al.
(author)
-
Lattice-Based Simulatable VRFs: Challenges and Future Directions
- 2018
-
In: Journal of Internet Services and Information Security. - 2182-2069 .- 2182-2077. ; 8:4, s. 57-69
-
Journal article (peer-reviewed)abstract
- Lattice-based cryptography is evolving rapidly and is often employed to design cryptographic primitives that hold a great promise to be post-quantum resistant and can be employed in multiple application settings such as: e-cash, unique digital signatures, non-interactive lottery and others. In such application scenarios, a user is often required to prove non-interactively the correct computation of a pseudo-random function F_k(x) without revealing the secret key k used. Commitment schemes are also useful in application settings requiring to commit to a chosen but secret value that could be revealed later. In this short paper, we provide our insights on constructing a lattice-based simulatable verifiable random function (sVRF) using non interactive zero knowledge arguments and dual-mode commitment schemes and we point out the main challenges that need to be addressed in order to achieve it.
|
|
7. |
- Hossain, Mohammad Shahadat, 1968-, et al.
(author)
-
A Belief Rule Based Expert System to Assess Hypertension under Uncertainty
- 2019
-
In: Journal of Internet Services and Information Security (JISIS). - Seoul, Republic of Korea : Innovative Information Science & Technology Research Group (ISYOU). - 2182-2069 .- 2182-2077. ; 9:4, s. 18-38
-
Journal article (peer-reviewed)abstract
- Hypertension (HPT) plays an important role, especially for stroke and heart diseases. Therefore, theaccurate assessment of hypertension is becoming a challenge. However, the presence of uncertainties, associated with the signs and symptoms of HPT are becoming crucial to conduct the preciseassessment. This article presents a web-based expert system (web BRBES) by employing beliefrule based (BRB) methodology to assess HPT, allowing the generation of reliable results. In order tocheck the reliability of the system, a comparison has been performed among various approaches suchas decision tree, random forest, artificial neural networks, fuzzy rule based expert system and experts’opinion. Different performance metrics such as confusion matrix, accuracy, root mean square error,area under curve have been used to contrast the reliability of the approaches. The BRBES producesa more reliable result than from the other approaches. Moreover, the user friendliness of the webBRBES found high as obtained by using the PACT (People, Activities, Contexts, Technologies) approach over 200 people.
|
|