Publications

Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering …

Since the majority of audio DeepFake (DF) detection methods are trained on English-centric datasets, their applicability to non-English …

Behavioural biometric systems based on typing errors rely on the natural tendency of people to make characteristic mistakes while …

Machine learning-based Android malware detectors are increasingly used in security products. However, they are vulnerable to backdoor …

We present a user authentication and identification system that leverages behavioural biometrics derived from typing errors. The system …