17 citations · 60 across the 24 of their papers we have counts for
7 papers · 1 filter
DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks
Seonhye Park, Alsharif Abuadbba, Shuo Wang +4
Training deep neural networks (DNNs) requires large datasets and powerful computing resources, which has led some owners to restrict redistribution without permission. Watermarking…
Reconstruction Attack on Differential Private Trajectory Protection Mechanisms
Erik Buchholz, Alsharif Abuadbba, Shuo Wang +2
Location trajectories collected by smartphones and other devices represent a valuable data source for applications such as location-based services. Likewise, trajectories have the…
Unraveling Threat Intelligence Through the Lens of Malicious URL Campaigns
Mahathir Almashor, Ejaz Ahmed, Benjamin Pick +6
The daily deluge of alerts is a sombre reality for Security Operations Centre (SOC) personnel worldwide. They are at the forefront of an organisation's cybersecurity infrastructure…
Profiler: Profile-Based Model to Detect Phishing Emails
Mariya Shmalko, Alsharif Abuadbba, Raj Gaire +3
Email phishing has become more prevalent and grows more sophisticated over time. To combat this rise, many machine learning (ML) algorithms for detecting phishing emails have been…
Deception for Cyber Defence: Challenges and Opportunities
David Liebowitz, Surya Nepal, Kristen Moore +6
Deception is rapidly growing as an important tool for cyber defence, complementing existing perimeter security measures to rapidly detect breaches and data theft. One of the factor…
PublicCheck: Public Integrity Verification for Services of Run-time Deep Models
Shuo Wang, Sharif Abuadbba, Sidharth Agarwal +6
Existing integrity verification approaches for deep models are designed for private verification (i.e., assuming the service provider is honest, with white-box access to model para…
Local Differential Privacy for Federated Learning
M. A. P. Chamikara, Dongxi Liu, Seyit Camtepe +4
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local diff…