Email Phishing: An Enhanced Classification Model to Detect Malicious URLs

Sankhwar, Shweta; Pandey, Dhirendra; Khan, Rquaiya

doi:10.4108/eai.13-7-2018.158529

Cited by 8 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anti-Phishing Multi-Filter (APMF) is developed with 25 heuristics that work as multi-layer filters. 7 APMF consists of five layers which are used to discriminate between the legitimate and phished URLs. APMF is consist of five layers, that is, Page Ranking, URL Property Values, Suspicious URL Forms or Patterns, Google suggestion for URL Authenticity and Social Feature Set (social human factor scanner) to identify the known and unknown phishing.…”

Section: Proposed Approach For E-mail Phishing Detectionmentioning

confidence: 99%

“…Pertinent 25 heuristics is identified through the exhaustive literature review, statistical investigations and analysis on phished and legitimate URLs/websites. 7,13 The implementation of this model is done in two phases. In phase I, Backpropagation learning algorithm and TRAINLIM (ie, Levenberg-Marquardt [LM] backpropagation) algorithm is employed.…”

Section: Proposed Approach For E-mail Phishing Detectionmentioning

confidence: 99%

“…Anti‐PhiEE is an email phishing detection model as shown in Figure 1. Anti‐Phishing Multi‐Filter (APMF) is developed with 25 heuristics that work as multi‐layer filters 7 . APMF consists of five layers which are used to discriminate between the legitimate and phished URLs.…”

Section: Proposed Approach For E‐mail Phishing Detectionmentioning

confidence: 99%

“…Research evidences suggest that the use of rule base phishing detection method has application in industry for identifying phishing attacks to analyze website information. As of now, many different phishing filtering approaches are existing with ML techniques such as logistic regression, Support Vector Machine, Markov Model, decision tree, and random forest for detecting phished URLs/links 7,8 . In this chapter, a novel approach for email phishing detection in enterprise environ is proposed with ANN.…”

Section: Introductionmentioning

confidence: 99%

“…As of now, many different phishing filtering approaches are existing with ML techniques such as logistic regression, Support Vector Machine, Markov Model, decision tree, and random forest for detecting phished URLs/links. 7,8 In this chapter, a novel approach for email phishing detection in enterprise environ is proposed with ANN.…”

mentioning

confidence: 99%

See 4 more Smart Citations

An anti‐phishing enterprise environ model using feed‐forward backpropagation and Levenberg‐Marquardt method

Sankhwar

Pandey

Khan

et al. 2020

Security and Privacy

Self Cite

View full text Add to dashboard Cite

Phishing in an enterprise is serious issue rising in wide scale and complexity, as phishers use email phishing via obfuscated, malicious or phished URLs and continuously adapt or innovate their strategies to lure victims for identity theft for financial benefits. To gain victim's trust and confidence phishers have started using visceral factors and familiarity cues. Phishing is not always money centric; phisher defame the user's goodwill and character. Defamation in enterprise could be much more traumatic than being embarrassed at a social networking site. It is a challenging task to address this issue. It is evident through literature review that single phishing detection filter approaches are insufficient to detect phishing in enterprise environ. Therefore, a novel anti-phishing model for enterprise using artificial neural network is proposed. In addition, this model effectively identifies whether the phishing email is known phishing or unknown phishing to reduce the trust and familiarity-based email phishing enterprise environ. The feed-forward backpropagation and Levenberg-Marquart methods of ANN are adopted to enhance the URL classification process and with Fuzzy Inference System to get result with imprecise data of social features. The proposed model can accurately classify the known and unknown email phishing via URLs. K E Y W O R D S authentication, E-mail phishing, enterprise cyber threat, machine learning techniques, privacy models for communication systems communication security, security and privacy in mobile communication services, social engineering 1 INTRODUCTION In digital era, email phishing is a critical issue causing loss of finance during online transactions. At present, different anti-phishing approaches are being proposed to detect email phishing attacks. Despite the various developed anti-phishing approaches are profoundly incompetent to tackle the real-time hassles. In literature review, a group of researchers argued upon about URLs blacklisting, which are mostly used in industry or organizations but not well off to

show abstract

Section: Proposed Approach For E-mail Phishing Detectionmentioning

confidence: 99%

Section: Proposed Approach For E-mail Phishing Detectionmentioning

confidence: 99%

Section: Proposed Approach For E‐mail Phishing Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

An anti‐phishing enterprise environ model using feed‐forward backpropagation and Levenberg‐Marquardt method

Sankhwar

Pandey

Khan

et al. 2020

Security and Privacy

Self Cite

View full text Add to dashboard Cite

show abstract

Cybercrime in India: An analysis of crime against women in ever expanding digital space

Sankhwar,

Ahuja,

Choubey

et al. 2023

Security and Privacy

Self Cite

View full text Add to dashboard Cite

The ever expanding digital space and government initiatives like Digital India have increased connectivity, digitization, remote employment which empowered us with technology and made our lifestyle easy and fast but as digitization is enhancing, cyberattacks are proportionally growing. In the initial stage of this study, it was observed from the data analysis and it was evident that women are particularly a soft target of many cybercriminals and cyber fraudsters. Women feel insecure in cyberspace, hence there is a need to dive deeper into our understanding and statistics of cybercrimes against women in India. It becomes necessary to determine the factors that have led to the clear surge of such crimes in recent years. In recent studies no such analysis is done focusing on geographical factors and top most cybercrime types committed against women. Therefore, in this article, prediction for cybercrime trends against women was performed using statistical tools and techniques to provide a better insight into the current scenario revolving around cybercrimes and women. A regressive statistical analysis of cybercrime data of all states of India to understand the current trend of cybercrimes, identification of the most vulnerable states of India and specific cybercrime with their percentage in whole, also where cybercrime afflicted women stand in those numbers. Further, for preventive measures a robust guidelines is proposed to combat cybercrimes for a better future.

show abstract