The role of artificial intelligence and machine learning in wireless networks security: principle, practice and challenges

Waqas, Muhammad; Tu, Shanshan; Halim, Zahid; Rehman, Sadaqat Ur; Abbas, Ghulam; Abbas, Ziaul Haq

doi:10.1007/s10462-022-10143-2

Cited by 82 publications

(37 citation statements)

References 164 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each layer of nodes in deep learning is trained on a different set of features from the previous layer’s output [ 51 , 52 ]. The deep network is taught to recognize more complex features as it goes deeper by aggregating and recombining features from previous layers [ 53 ].…”

Section: Evaluation With Resunetmentioning

confidence: 99%

A Deep Learning Approach for Liver and Tumor Segmentation in CT Images Using ResUNet

et al. 2022

Self Cite

View full text Add to dashboard Cite

According to the most recent estimates from global cancer statistics for 2020, liver cancer is the ninth most common cancer in women. Segmenting the liver is difficult, and segmenting the tumor from the liver adds some difficulty. After a sample of liver tissue is taken, imaging tests, such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US), are used to segment the liver and liver tumor. Due to overlapping intensity and variability in the position and shape of soft tissues, segmentation of the liver and tumor from computed abdominal tomography images based on shade gray or shapes is undesirable. This study proposed a more efficient method for segmenting liver and tumors from CT image volumes using a hybrid ResUNet model, combining the ResNet and UNet models to address this gap. The two overlapping models were primarily used in this study to segment the liver and for region of interest (ROI) assessment. Segmentation of the liver is done to examine the liver with an abdominal CT image volume. The proposed model is based on CT volume slices of patients with liver tumors and evaluated on the public 3D dataset IRCADB01. Based on the experimental analysis, the true value accuracy for liver segmentation was found to be approximately 99.55%, 97.85%, and 98.16%. The authentication rate of the dice coefficient also increased, indicating that the experiment went well and that the model is ready to use for the detection of liver tumors.

show abstract

Section: Evaluation With Resunetmentioning

confidence: 99%

A Deep Learning Approach for Liver and Tumor Segmentation in CT Images Using ResUNet

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, an extensive survey on AI solutions for security threats is given in [ 25 ]. There, a taxonomy of cyber vulnerabilities is given in the context of, among others, cloud-based scenarios.…”

Section: Related Workmentioning

confidence: 99%

Robust Financial Fraud Alerting System Based in the Cloud Environment

Stojanović

Božić

2022

Sensors

View full text Add to dashboard Cite

The digitalisation of finance influenced the emergence of new technological concepts for existing user needs. Financial technology, or fintech, provides improved services for customers and new economic value for businesses. As such, fintech services require on-demand availability on a 24/7 basis. For this reason, they are often deployed in cloud environments that allow connectivity with ubiquitous devices. This allows customers to perform online transactions, which are overseen by the respective financial institutions. However, such cloud-based systems introduce new challenges for information security. On one hand, they represent attractive targets for cyberattacks. On the other, financial frauds can still go unnoticed by the financial institutions in charge. This paper contributes to both challenges by introducing the concept for a cloud-based system architecture for fraud detection and client profiling in the banking domain. Therefore, a systematic risk assessment was conducted in this context, and exploitation probabilities were inferred for multiple attack scenarios. In addition, formal verification was accomplished in order to determine the effects of successful vulnerability exploits. The consequences of such security violations are discussed, and considerations are given for improving the resilience of fintech systems.

show abstract

“…Impersonation attack to device-to-device communications can be easily performed [8], and the security problem becomes aggravated with the proliferation of wireless devices [9]. Since trusted third party can mitigate the risk between end devices for remote transaction, many researchers work on data exchanges based on the blockchain.…”

Section: Related Workmentioning

confidence: 99%

Multi-party Non-interactive Atomic Fair Data Exchange based on Blockchain

Zhan

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

Widely adopted blockchain-based fair data exchange protocol have the following problems in multi-party scenario: 1) in multi-buyer v.s. one seller scenario, the negotiation for data availability verification between the buyer and seller reduces transaction throughput greatly. Besides, malicious buyers can launch DoS attacks to prevent the seller from serving others by requiring lots of data availability proofs. 2) in multi-seller v.s. one buyer scenario where the buyer pays for the merged data of all sellers, current protocols treat this as multiple independent transactions, resulting in excessive on-chain costs. Moreover, current protocols neglect that data ownership establishment on-chain may be tampered since the registration info is in plaintext and submitted through the Internet. This paper proposes multi-party non-interactive atomic fair data exchange protocol based on blockchain to solve the above problems, providing data confidentiality, transaction atomic fairness, data intellectual property right protection, and high efficiency. Specifically, we propose transparent zero knowledge proof-based data verification guaranteeing the data confidentiality and transaction fairness. With the proof computed once and used everywhere, transaction throughput is improved greatly and DoS attacks initiated by malicious buyers is prevented. Moreover, the agent representing multi-seller is introduced to reduce on-chain costs. Furthermore, two-stage on-chain ownership registration is proposed to prevent eavesdroppers from impersonating the owner. Finally, we implement a POC (Proof of Concept) of our protocol as the BADE (Blockchain-based multi-party non-interactive Atomic fair Data Exchange). Experiments show that, our throughput within 12 hours is 50 times that of existing solution\cite{ref10}. And in multi-seller scenario, the on-chain gas costs of our protocol is reduced by 19.9\%-30.5\% in different seller/buyer ratios. The fairness of data exchange is also ensured by extra gas costs of dishonest party.

show abstract

The role of artificial intelligence and machine learning in wireless networks security: principle, practice and challenges

Cited by 82 publications

References 164 publications

A Deep Learning Approach for Liver and Tumor Segmentation in CT Images Using ResUNet

A Deep Learning Approach for Liver and Tumor Segmentation in CT Images Using ResUNet

Robust Financial Fraud Alerting System Based in the Cloud Environment

Multi-party Non-interactive Atomic Fair Data Exchange based on Blockchain

Contact Info

Product

Resources

About