About: FedEmail: Performance Measurement of Privacy-friendly Phishing Detection Enabled by Federated Learning

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: FedEmail: Performance Measurement of Privacy-friendly Phishing Detection Enabled by Federated Learning Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	FedEmail: Performance Measurement of Privacy-friendly Phishing Detection Enabled by Federated Learning
Creator	Tang, Abuadbba, Sharif Almashor, Australia, Mahathir Australia, Seyit Camtepe, Data61, Data61, Australia Gao, Yansong Jun, Wen Thapa, Chandra Zheng, Yifeng
Source	ArXiv
abstract	Artificial intelligence (AI) has been applied in phishing email detection. Typically, it requires rich email data from a collection of sources, and the data usually contains private information that needs to be preserved. So far, AI techniques are solely focusing on centralized data training that eventually accesses sensitive raw email data from the collected data repository. Thus, a privacy-friendly AI technique such as federated learning (FL) is a desideratum. FL enables learning over distributed email datasets to protect their privacy without the requirement of accessing them during the learning in a distributed computing framework. This work, to the best of our knowledge, is the first to investigate the applicability of training email anti-phishing model via FL. Building upon the Recurrent Convolutional Neural Network for phishing email detection, we comprehensively measure and evaluate the FL-entangled learning performance under various settings, including balanced and imbalanced data distribution among clients, scalability, communication overhead, and transfer learning. Our results positively corroborate comparable performance statistics of FL in phishing email detection to centralized learning. As a trade-off to privacy and distributed learning, FL has a communication overhead of 0.179 GB per global epoch per its clients. Our measurement-based results find that FL is suitable for practical scenarios, where data size variation, including the ratio of phishing to legitimate email samples, among the clients, are present. In all these scenarios, FL shows a similar performance of testing accuracy of around 98%. Besides, we demonstrate the integration of the newly joined clients with time in FL via transfer learning to improve the client-level performance. The transfer learning-enabled training results in the improvement of the testing accuracy by up to 2.6% and fast convergence.
has issue date	2020-07-27(xsd:dateTime)
has license	arxiv
sha1sum (hex)	4cb12d28a29e9ec99ff45a8ec89b0d17e9817f8b
resource representing a document's title	FedEmail: Performance Measurement of Privacy-friendly Phishing Detection Enabled by Federated Learning
resource representing a document's body	covid:4cb12d28a29e9ec99ff45a8ec89b0d17e9817f8b#body_text
is schema:about of	named entity 'accessing' named entity 'Performance Measurement' named entity 'TECHNIQUES' named entity 'IS A' named entity 'COLLECTED' named entity 'DATA' named entity 'NEEDS' named entity 'PRIVATE' named entity 'USUALLY' named entity 'RICH' named entity 'THEIR' named entity 'data repository' named entity 'collection' named entity 'Thus' named entity 'model' named entity 'distributed' named entity 'centralized' named entity 'raw' named entity 'Artificial intelligence' named entity 'email' named entity 'email' named entity 'email' named entity 'Phishing' named entity 'focusing' named entity 'homomorphic encryption' named entity 'current dataset' named entity 'Tokenizer' named entity 'Convolutional Neural Network' named entity 'phishing' named entity 'scalability' named entity 'cryptographic' named entity 'phishing attacks' named entity 'learning process' named entity 'data packet' named entity 'personally identifying information' named entity 'email header' named entity 'phishing email' named entity 'transfer learning' named entity 'email' named entity 'anti-phishing' named entity 'good performance' named entity 'collaborative learning' named entity 'feature selection' named entity 'server' named entity 'phishing' named entity 'Convolutional Neural Network' named entity 'email' named entity 'data integration' named entity 'Computing' named entity 'Cooperative Research Centre' named entity 'email' named entity 'email' named entity 'Decision Tree' named entity 'learning process' named entity 'email header' named entity 'email' named entity 'phishing email' named entity 'email' named entity 'email' named entity 'feature engineering' named entity 'model training' named entity 'large number' named entity 'federated learning' named entity 'social graphs' named entity 'anti-phishing' named entity 'natural language processing' named entity 'plain text' named entity 'transfer learning' named entity 'learning process' named entity 'differential privacy' named entity 'federated learning' named entity 'email' named entity 'encrypted data' named entity 'stopwords' named entity 'Long Short-Term Memory' named entity 'plain text'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software