# Detecting Cybersecurity Events from Noisy Short Text

## TL;DR

This paper introduces a neural network-based approach combining domain-specific embeddings and task features to detect cybersecurity events from noisy social media texts, specifically tweets, outperforming traditional methods.

## Contribution

It presents a novel CNN-LSTM model utilizing meta-embeddings and contextual features for cybersecurity event detection in noisy short texts, along with a new annotated Twitter dataset.

## Key findings

- Proposed model outperforms traditional baselines
- Effective detection of cybersecurity events from noisy tweets
- New annotated dataset of cybersecurity-related tweets

## Abstract

It is very critical to analyze messages shared over social networks for cyber threat intelligence and cyber-crime prevention. In this study, we propose a method that leverages both domain-specific word embeddings and task-specific features to detect cyber security events from tweets. Our model employs a convolutional neural network (CNN) and a long short-term memory (LSTM) recurrent neural network which takes word level meta-embeddings as inputs and incorporates contextual embeddings to classify noisy short text. We collected a new dataset of cyber security related tweets from Twitter and manually annotated a subset of 2K of them. We experimented with this dataset and concluded that the proposed model outperforms both traditional and neural baselines. The results suggest that our method works well for detecting cyber security events from noisy short text.