ML

Multilingual Audio DeepFake Detection
Can state-of-the-art audio deepfake detectors generalise beyond English? A benchmark across 8 languages reveals significant gaps — and a path forward.
Code Paper
Defending ML-based Android Malware Detectors Against Backdoor Attacks
Machine learning powers modern Android malware detection — but it is vulnerable to backdoor attacks. We propose a feature-selection defence that reduces this risk without sacrificing accuracy.
Securing ML-based Android Malware Detectors: A Defensive Feature Selection Approach against Backdoor Attacks
Machine learning-based Android malware detectors are increasingly used in security products. However, they are vulnerable to backdoor …
Bartłomiej Marek, Kacper Pieniążek, Filip Ratajczak, Wojciech Adamczyk, Bartosz Bok, Mateusz Krzysztoń
Jul 2024
Cite Project
Behavioural Biometric System Based on Typing Errors
People make characteristic mistakes when they type. Can those mistakes serve as a biometric signature for authentication? This project built — and rigorously evaluated — a system that answers yes.