# Training Transformers for Information Security Tasks: A Case Study on Malicious URL Prediction

arXiv: https://arxiv.org/abs/2011.03040 · HTML: https://mlsanity.com/paper/2011.03040/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 3 of 3)

- [Recasting Self-Attention with Holographic Reduced Representations](https://mlsanity.com/paper/2305.19534/) (2023)
- [Web Content Filtering through knowledge distillation of Large Language Models](https://mlsanity.com/paper/2305.05027/) (2023)
- [A Transformer-based Model to Detect Phishing URLs](https://mlsanity.com/paper/2109.02138/) (2021)

## Abstract (arXiv)

Machine Learning (ML) for information security (InfoSec) utilizes distinct data types and formats which require different treatments during optimization/training on raw data. In this paper, we implement a malicious/benign URL predictor based on a transformer architecture that is trained from scratch. We show that in contrast to conventional natural language processing (NLP) transformers, this model requires a different training approach to work well. Specifically, we show that 1) pre-training on a massive corpus of unlabeled URL data for an auto-regressive task does not readily transfer to malicious/benign prediction but 2) that using an auxiliary auto-regressive loss improves performance when training from scratch. We introduce a method for mixed objective optimization, which dynamically balances contributions from both loss terms so that neither one of them dominates. We show that this method yields performance comparable to that of several top-performing benchmark classifiers.