Exquisite Analysis of Popular Machine Learning–Based Phishing Detection Techniques for Cyber Systems

Das, Meenakshi; Saraswathi, S.; Panda, Rashmi; Mishra, Alekha Kumar; Tripathy, Asis Kumar

doi:10.1080/19361610.2020.1816440

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This scan processes accessibility scan messages that seek to confirm the actual caller ID and display name using a gateway, which is aware of the call's actual caller ID. Furthermore, Nakkala Srinivas Mudiraj et al [23] proposed detecting phishing Web sites using different machine-learning models. The model is designed to detect phishing or not in R and calculate the accuracy rate of various techniques by taking various features of the URLS and conducting a lexical analysis.…”

Section: Related Workmentioning

confidence: 99%

Characterizing Mobile Money Phishing Using Reinforcement Learning

Njoya,

Ngongag,

Tchakounté

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Mobile money helps people accumulate, send and receive money using their mobile phones without having a bank account (i.e., in some African countries). Such technology is heavily and efficiently used in many areas where bank services are unavailable and/or in crisis (i.e., during the Covid-19 pandemic) when transportation and services are limited. However, malicious users such as scammers have leveraged social engineering techniques to abuse mobile money services through scams, and frauds, among others. Existing countermeasures, which are specific to mobile money security, mostly ignore the dynamic aspect of interactions between the malicious party and the victim. Considering the above insufficiency, this paper proposes a new approach to characterize mobile money phishing attacks based on reinforcement learning (RL) through Q−learning and Markov decision processes (MDP) and on deep reinforcement learning (DRL) through DRL algorithms, namely, Deep sarsa, Advantage Actor-Critic (A2C), Deep Deterministic Policy Gradient (DDPG), and Deep Q-learning (DQN). In fact, the proposed approach models the optimal sequences of attacker actions to achieve their goals through reinforcement learning and deep reinforcement methods. We experiment on real attack scenarios that have been encountered at Orange and MTN telecoms. Furthermore, we compared reinforcement learning and deep reinforcement learning algorithms to each other and thereby demonstrated the difference between them. This analysis showed a better performance in learning with RL. We also deduced that Q− learning takes less execution time than CDM and therefore its learning quality is better for characterizing mobile money phishing attacks. Finally, we found that some deep reinforcement algorithms, such as Deep Sarsa and A2C, can improve the characterization of scammervictim interactions during mobile payments.

show abstract

Section: Related Workmentioning

confidence: 99%

Characterizing Mobile Money Phishing Using Reinforcement Learning

Njoya,

Ngongag,

Tchakounté

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Additionally, Kikwasi [53] and Amina et al [54] assert that the main reasons for project interruption involve suspensions, liquidation, bankruptcy, delayed payment, cash flow issues, stakeholders' non-payment and schedule slippage. Thus, good data management risk through the use of ML techniques such as fuzzy control, WEKA, and ANN, among others, can help detect phishing [55] and prevent the execution of construction projects by avoiding various risks. However, construction parties need to be constantly updated on the new and various project risks to keep the same level of control over the project finances, execution and performance [15].…”

Section: Project Execution Interruption and Financial Lossesmentioning

confidence: 99%

Data Management Risks: A Bane of Construction Project Performance

et al. 2022

View full text Add to dashboard Cite

The construction industry is a sector that creates employment opportunities for everybody from all backgrounds. A good performance achieved through managing data is one factor that enables the construction industry’s success and development. Unfortunately, data management encounters challenges regarding data safety, due to the implementation of the fourth industrial revolution (4IR) (digitalisation). This study sets out to evaluate the effects of risks to data management on the performance of construction projects. This research work used a quantitative methodology and gathered information from different construction professionals in the South African construction industry via a well-structured questionnaire through online platforms. These professionals were quantity surveyors, architects, civil, mechanical, and electrical engineers practising for a firm, company, organization, or institution within Gauteng province, South Africa. A random sampling technique was used in this research to ensure that each part and set of individuals had an equivalent possibility of being incorporated into the sample. Of 215 questionnaires sent out, 181 (84.19%) responses were received and used for data analysis. Mean item score (MIS), standard deviation (SD), a non-parametric test, and exploratory factor analysis were used to analyse the retrieved data. Findings revealed that loss of construction project data, loss of confidential information, company image and reputational harm are among the top three effects that risks to data have on people working in the construction sector. This study concluded that these data management risk effects could be prevented if construction project stakeholders were aware of the different data management risks.

show abstract