China
Africa
Explore chapters and articles related to this topic
Introduction to Machine Learning through Hands-on in Python
Published in Pushpa Singh, Divya Mishra, Kirti Seth, Transformation in Healthcare with Emerging Technologies, 2022
Ranjit Varma, Devendra Bharadwaj
As the name suggests, this branch of Machine Learning involves training a machine to learn from already existing data and outcomes. Supervised Learning can handle two categories of problems, one that requires Classification or identification of categories, and second, Regression, which requires a discrete numerical output derived. Let’s understand Classification first. Recall the previous example that we discussed for filtering a spam mail. In order to identify whether a mail is a spam or not, your program or machine will have to be trained to identify the characteristics of a spam mail. For this you may either pass some keywords which are usually a part of spam mail e.g., “lottery,” “sale,” “free credit”, etc. With this you’ll also have to tag or label the mails having these as either part of their body or headlines. Now, you train your machine with all these ‘labeled’ mails. Once your machine is trained with a certain degree of accuracy, you can now use it to classify an entire new set of mails as spam or not. This is how supervised learning is used for classification problems. Though the spam mail discussed is an example of binary classification, supervised learning also covers multi-classification problems, e.g., when used with animal images to identify fish, dog, or cat.
Adversarial Attacks and Defenses against Deep Learning in Cybersecurity
Published in Neeraj Mohan, Surbhi Gupta, Chuan-Ming Liu, Society 5.0 and the Future of Emerging Computational Technologies, 2022
Huge adversaries and cybercrimes are evolving in the field of social engineering attacks. Spam is a type of junk mail sent to an email address. Spam does not only include unsolicited commercial emails; sometimes, they may be fraudulent messages. These dangerous types of spam may clog the information stored and damage the network as well. The filtering of spam can be done based on the textual information of the emails. Many AI algorithms, like Naïve Bayes (NB), term frequency-inverse document frequency (TF-IDF) and SVM, will boost up the filtration of spam mail and prevent fraudulent messages. By using advanced techniques, like deep neural networks (DNNs) and case-based reasoning fuzzy logic systems, these kinds of crimes are being prevented to some extent (Lansley et al. 2019). As an advanced technique, the suspected emails can be analyzed based upon feature vectors, such as attachments, mail size, IP address as well as the address of the recipient and sender of the email. To have such deep analysis of detecting cybercrime, advanced SVM and DNN methods are used in cybersecurity applications.
Email Spam and Malware Filtering Using Machine Learning and Its Applications
Published in Madhu Arora, Poonam Khurana, Sonam Choiden, Performance Management, 2020
Sachin Kumar, Sandeep Kumar Mittal
Spammers may sometimes include unsafe attachments, or connections to websites for phishing purposes. These spams threaten the privacy and safety of vast quantities of sensitive information. Here, we strive to create malicious spam findings throughout the choice of features. Unwanted emails, known as spam, are one of today's fast-growing and expensive Internet-related issues. Email is used by millions of individuals around the globe every day to interact and is a mission-critical tool for many companies. Unwanted bulk email has become an issue over time. An overwhelming quantity of spam flows into the mailboxes of email users every day. For most email users, spam is not only frustrating, but dangerous, as it may contain unsafe attachments or connections to websites for phishing purposes. Here, we provide an effective spam filter technique based on the Naive Bayes Classifier to filter unwanted spam email. Bayesian filtering operates by assessing the likelihood of distinct phrases appearing in lawful and spam emails, then classifying emails according to those probabilities.
The psychological interaction of spam email features
Published in Ergonomics, 2019
Sarah E. Williams, Dawn M. Sarno, Joanna E. Lewis, Mindy K. Shoss, Mark B. Neider, Corey J. Bohil
The current research focussed on the psychological basis for classifying spam or phishing emails. Spam is commonly defined as unsolicited bulk emails. Phishing is more insidious, often including overt or covert requests for data which can lead to theft. As statistical filters improve, spammers learn techniques to circumvent them, thus leaving some burden on email recipients. Lowd and Meek (2005) assessed the effectiveness of filters against ‘good word’ attacks or spam messages loaded with extra words common to legitimate emails. They show frequent retraining is the only way to keep filters viable. Other researchers have focussed on machine learning in their efforts to support cybersecurity (Hayden 2015; Wu et al. 2005; Youn and McLeod 2007). However, filters – thorough as they may be – will not catch every spam email. Users must have their own understanding of spam in order to combat the issue.
VGI and crowdsourced data credibility analysis using spam email detection techniques
Published in International Journal of Digital Earth, 2018
Saman Koswatte, Kevin McDougall, Xiaoye Liu
Spam email is considered as ‘unsolicited bulk email’ in its shortest definition (Blanzieri and Bryl 2008). Spam emails cost industries billions of dollars annually through the misuse of computing resources and the additional time required by users to sort emails. Spam emails can often carry computer viruses and also violate users’ privacy (Blanzieri and Bryl 2008). Compared to the spam emails, CSD has some similarities and differences. Firstly, CSD also has a mixture of content that varies in credibility and the CSD events often generate large volumes of data. Emails, including spam emails, often have a specified structure (sender, body text and header), however, CSD often lacks structure. Finally, the aim of the filtering data to identify legitimate or credible content is similar in both cases.
Cybersecurity for children: an investigation into the application of social media
Published in Enterprise Information Systems, 2023
Victor Chang, Lewis Golightly, Qianwen Ariel Xu, Thanaporn Boonmee, Ben S. Liu
Spam attacks occur when hackers know about the victim’s communication details and send spam or junk data via emails. Spam emails can increase the victim’s cost of using email and may cause network congestion (Truong, Diep, and Zelinka 2020). Social network administrators use filters to check and mark which emails are spam to mitigate such problems. Thus, the spam report can also help users avoid the messages inside spam emails received in their email inboxes.