# Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation

arXiv: https://arxiv.org/abs/2404.01940 · HTML: https://mlsanity.com/paper/2404.01940/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 8 of 8)

- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [MTNT: A Testbed for Machine Translation of Noisy Text](https://mlsanity.com/paper/1809.00388/) (2018)
- [Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go](https://mlsanity.com/paper/2103.00153/) (2021)
- [Fine-tuning GPT-3 for Russian Text Summarization](https://mlsanity.com/paper/2108.03502/) (2021)
- [Using Deep Neural Networks to Translate Multi-lingual Threat Intelligence](https://mlsanity.com/paper/1807.07517/) (2018)
- [Towards Dark Jargon Interpretation in Underground Forums](https://mlsanity.com/paper/2011.03011/) (2020)

## Abstract (arXiv)

Understanding cybercrime communications is paramount for cybersecurity defence. This often involves translating communications into English for processing, interpreting, and generating timely intelligence. The problem is that translation is hard. Human translation is slow, expensive, and scarce. Machine translation is inaccurate and biased. We propose using fine-tuned Large Language Models (LLM) to generate translations that can accurately capture the nuances of cybercrime language. We apply our technique to public chats from the NoName057(16) Russian-speaking hacktivist group. Our results show that our fine-tuned LLM model is better, faster, more accurate, and able to capture nuances of the language. Our method shows it is possible to achieve high-fidelity translations and significantly reduce costs by a factor ranging from 430 to 23,000 compared to a human translator.