User identification via neural network based language models
TD Phan, N Zincir‐Heywood - International Journal of Network …, 2019 - Wiley Online Library
Identifying compromised accounts on online social networks that are used for phishing
attacks or sending spam messages is still one of the most challenging problems of cyber …
attacks or sending spam messages is still one of the most challenging problems of cyber …
Classification of micro-texts using sub-word embeddings
M Joshi, N Zincir-Heywood - Proceedings of the International …, 2019 - aclanthology.org
Extracting features and writing styles from short text messages is always a challenge. Short
messages, like tweets, do not have enough data to perform statistical authorship attribution …
messages, like tweets, do not have enough data to perform statistical authorship attribution …
A language model for compromised user analysis
TD Phan, AN Zincir-Heywood - NOMS 2018-2018 IEEE/IFIP …, 2018 - ieeexplore.ieee.org
Identifying compromised accounts on online social networks that are used for phishing
attacks or sending spam messages is still one of the most challenging problems of cyber …
attacks or sending spam messages is still one of the most challenging problems of cyber …