13 citations · 20 across the 7 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks
Xiaoyun Xu, Oguzhan Ersoy, Stjepan Picek
Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (bac…
cs.LG2021★ 2 cited
Watermarking Graph Neural Networks based on Backdoor Attacks
Jing Xu, Stefanos Koffas, Oguzhan Ersoy +1
Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amo…