Cascaded Simple Filters for Accurate and Lightweight Email-Spam Detection

Takesue, Masaru

doi:10.1109/securware.2010.34

Cited by 3 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, even if the full-blown level I implementation has a false negative rate FN1, and the weak level II implementation only FN2, the overall false rate is improved as FN1*FN2. Indeed, improving false negative rates with lightweight cascaded classifiers found its way into practical implementations with e-mail spam filters more than a decade ago [16].…”

Section: A Architectural Approachmentioning

confidence: 99%

Anomaly Detection in IoT Networks: From Architectures to Machine Learning Transparency

Huc

Trček

2021

IEEE Access

View full text Add to dashboard Cite

Machine learning (ML) is becoming an integral part of networks security arsenal, where Internet of Things (IoT) structures play an increasingly important role. However, IoT networks have many specific requirements, mostly due to limited energy availability and stringent computing resources. This results in limitations for traditional ML approaches to security, in particular for anomaly detection. Consequently, new focuses for solutions that range from architectural to data processing ones are necessary. Therefore, appropriate lightweight ML algorithms have to be designed and deployed in appropriate architectural settings, which is the main contribution of this paper. In addition, insights into ML functioning are needed to better understand the observed anomalies. To enable these insights (and support a wider applicability of ML based approaches), the results have to be as explainable as possible. The research presented in this paper addresses this problem through the functional and data transparency of ML applications, tailored to the specifics of anomaly detection in IoT networks. To tackle accordingly also the architectural issues, the presented approach builds on the well-established layering principle from computer communications reference models. This principle not only supports flexibility but also increases security in these new environments of growing importance.

show abstract

Section: A Architectural Approachmentioning

confidence: 99%

Anomaly Detection in IoT Networks: From Architectures to Machine Learning Transparency

Huc

Trček

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Email Signatures; Trojans can spoof sender's address to reflect well known organisations such as banks, power companies and post office. A signature based on these known malicious trends can be created along with a blocking rule on an IDS to prevent users from receiving such emails [111], [112]. Although this strategy can be easily bypassed by adversaries, it is still effective in the absence of adversaries' knowledge of being shunned.…”

Section: Host Based Detectionmentioning

confidence: 99%

“…As Trojans are mostly delivered though unsolicited emails (referred to as spam) [125], analysis of these emails can lead to establishment of a pattern or a detection matrix . Filters can be set to scan for specific fingerprints from subject headers, message bodies, white and even black lists email addresses [111], [112].…”

Section: Analysis Of Spam Records;mentioning

confidence: 99%

A cyber kill chain based taxonomy of banking Trojans for evolutionary computational intelligence

Kiwia

Dehghantanha

Choo

et al. 2018

Journal of Computational Science

View full text Add to dashboard Cite

Malware such as banking Trojans are popular with financially-motivated cybercriminals. Detection of banking Trojans remains a challenging task, due to the constant evolution of techniques used to obfuscate and circumvent existing detection and security solutions. Having a malware taxonomy can facilitate the design of mitigation strategies such as those based on evolutionary computational intelligence. Specifically, in this paper, we propose a cyber kill chain based taxonomy of banking Trojans features. This threat intelligence based taxonomy providing a stage-by-stage operational understanding of a cyber-attack, can be highly beneficial to security practitioners and the design of evolutionary computational intelligence on Trojans detection and mitigation strategy. The proposed taxonomy is validated by using a real-world dataset of 127 banking Trojans

show abstract

Comparison of Novel Recurrent Neural Network Over Artificial Neural network in Predicting Email spammers with improved accuracy

Neeharika,

Kalaiarasi

2023

E3S Web Conf.

View full text Add to dashboard Cite

The main aim is to compare Novel Recurrent Neural Network over Artificial Neural Network in predicting Email spammers with improved accuracy. Material and Methods : This research study contains two groups namely Novel Recurrent Neural Network and Artificial Neural Network. Each group consists of a sample size of 10 and the study parameters are calculated using clincalc with preset parameters as alpha 0.8, beta 0.2 and CI as 90%. Results and Discussion : The Novel Recurrent Neural Network has the highest accuracy 97.96% when compared to Artificial Neural Network it has 93.79% accuracy in Electronic Mail spam prediction with significance value p=0.000(p<0.05) that is significantly better. The G-power value is 80%. When used as a spam predictor for electronic mail, the Novel Recurrent Neural Network performance analysis outperforms the best results than the Artificial Neural Network performance.

show abstract

Cascaded Simple Filters for Accurate and Lightweight Email-Spam Detection

Cited by 3 publications

References 19 publications

Anomaly Detection in IoT Networks: From Architectures to Machine Learning Transparency

Anomaly Detection in IoT Networks: From Architectures to Machine Learning Transparency

A cyber kill chain based taxonomy of banking Trojans for evolutionary computational intelligence

Comparison of Novel Recurrent Neural Network Over Artificial Neural network in Predicting Email spammers with improved accuracy

Contact Info

Product

Resources

About