Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Read by thought-leaders and decision-makers around the world. Phone Number: +1-650-246-9381 Email: [email protected]
228 Park Avenue South New York, NY 10003 United States
Website: Publisher: https://towardsai.net/#publisher Diversity Policy: https://towardsai.net/about Ethics Policy: https://towardsai.net/about Masthead: https://towardsai.net/about
Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Founders: Roberto Iriondo, , Job Title: Co-founder and Advisor Works for: Towards AI, Inc. Follow Roberto: X, LinkedIn, GitHub, Google Scholar, Towards AI Profile, Medium, ML@CMU, FreeCodeCamp, Crunchbase, Bloomberg, Roberto Iriondo, Generative AI Lab, Generative AI Lab Denis Piffaretti, Job Title: Co-founder Works for: Towards AI, Inc. Louie Peters, Job Title: Co-founder Works for: Towards AI, Inc. Louis-François Bouchard, Job Title: Co-founder Works for: Towards AI, Inc. Cover:
Towards AI Cover
Logo:
Towards AI Logo
Areas Served: Worldwide Alternate Name: Towards AI, Inc. Alternate Name: Towards AI Co. Alternate Name: towards ai Alternate Name: towardsai Alternate Name: towards.ai Alternate Name: tai Alternate Name: toward ai Alternate Name: toward.ai Alternate Name: Towards AI, Inc. Alternate Name: towardsai.net Alternate Name: pub.towardsai.net
5 stars – based on 497 reviews

Frequently Used, Contextual References

TODO: Remember to copy unique IDs whenever it needs used. i.e., URL: 304b2e42315e

Resources

Unlock the full potential of AI with Building LLMs for Productionβ€”our 470+ page guide to mastering LLMs with practical projects and expert insights!

Publication

Text Augmentation for detecting spear-phishing emails
Natural Language Processing

Text Augmentation for detecting spear-phishing emails

Last Updated on October 23, 2020 by Editorial Team

Author(s): Edward Ma

Natural Language Processing

Text Augmentation for Detecting Spear-phishing Emails

Text augmentation techniques for phishing email detection

Photo by James Wheeler onΒ Unsplash

Information security is very important for any organization. Lost money is a minor problem, the serious one is that the enterprise system. However, fraud email and phishing email occupy a small set of data when comparing to normal email. Augmenting fraud and phishing email is a way to tackle thisΒ problem.

Example of CEO fraud email (Regina et al.,Β 2020)

Therefore, Regina et al. proposed three different approaches to generate synthetic data for model training. As synthetic data is a kind of β€œfake” data, some low-quality data may hurt model performance. Validations are needed to keep a high-quality synthetic data. Also, there are some assumptions whichΒ are:

  • Synthetic data should share the same label as the original text. For example, synthetic data should be change label from positive to negative (for binary classifier).
  • Synthetic data should not be redundant. In other words, the augmented text should not be almost identical to the originalΒ text.
Above: Original Text. Below: Augmented Text (Regina et al.,Β 2020)
Replacements performed (Regina et al.,Β 2020)

Word Replacement

Abbreviations Replacement

Abbreviations are very common in daily conversation. It allows the speaker and audience can communicate easier. For example, β€œF/W” and β€œFW” means β€œforward”. However, there are some vague scenarios that we need context to interpret the abbreviations. For instance, β€œPM” can be interpreted as β€œProject Manager” and β€œPrime Minister”.

Although this method is easy to understand and implement, the drawback is that it needs to define the conversion or mapping one byΒ one.

Example of abbreviations replacement

Misspellings Replacement

Although auto-complete helps to correct misspellings, typo still exists in email and social media. For example, β€œbargin” is a typo of β€œbargain”. Regina et al. mentioned that misspellings are important because:

  • Misspellings can convey a sense ofΒ urgency
  • Misspellings can fool security technologies based on text analysis.
Example of misspellings replacement.

This method helps to tackle potential unseen text in inference time as the model may be trained with those misspellings tokens.

Synonym Replacement

By replacing similar meaning words, it can become a new training for models. Regina et al. used both WordNet and BERT to find synonyms or near-synonyms. For example, β€œThe quick brown fox jumps over the lazy dog.” and β€œLittle quick brown fox jumps over the lazy dog.” have similar meanings. The second sentence is generated by the BERTΒ model.

Example of near-synonym replacement.

Leveraging WordNet is a typical way to generate synthetic while leveraging BERT to find near-synonyms is a better way to achieve it. ReasonsΒ are:

  • BERT or contextual word embeddings model can generate near-synonyms words. It introduces more synthetic data and no need to pre-defined a list of synonyms (i.e.Β WordNet)
  • As BERT can be trained for domain-specific knowledge, it can apply to specific domainΒ data.

Take Away

  • Generating training data helps to tackle low resource problems. However, bear in mind that you should select appropriate methods to generate synthetic data.
  • Some free open source libraries provide an easy way to generate synthetic data. nlpaug is one of the examples that you can generate data by several lines ofΒ code.

About Me

I am a Data Scientist in the Bay Area. Focusing on state-of-the-art work in Data Science, Artificial Intelligence, especially in NLP and platform related. Feel free to connect with me on LinkedIn or follow me on Medium orΒ Github.

Extension Reading

  • A library of Data Augmentation for NLPΒ (nlpaug)

Reference


Text Augmentation for detecting spear-phishing emails was originally published in Towards AI on Medium, where people are continuing the conversation by highlighting and responding to this story.

Published via Towards AI

Feedback ↓