@inproceedings{10.1145/3319535.3363267,
author = {Verma, Rakesh M. and Zeng, Victor and Faridi, Houtan},
title = {Data Quality for Security Challenges: Case Studies of Phishing, Malware and Intrusion Detection Datasets},
year = {2019},
isbn = {9781450367479},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3319535.3363267},
doi = {10.1145/3319535.3363267},
abstract = {Techniques from data science are increasingly being applied by researchers to security challenges. However, challenges unique to the security domain necessitate painstaking care for the models to be valid and robust. In this paper, we explain key dimensions of data quality relevant for security, illustrate them with several popular datasets for phishing, intrusion detection and malware, indicate operational methods for assuring data quality and seek to inspire the audience to generate high quality datasets for security challenges.},
booktitle = {Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security},
pages = {2605–2607},
numpages = {3},
keywords = {data poisoning, data quality, semiotics, data difficulty},
location = {London, United Kingdom},
series = {CCS '19}
}