3 papers
cs.CR2025
WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks
Tingzhi Li, Xuefeng Liu, Jing Lei +1
Graph Neural Networks (GNNs) are increasingly deployed in real-world applications, making ownership verification critical to protect their intellectual property against model theft…
cs.LG2024
: A Library for Efficient Data Attribution
Junwei Deng, Ting-Wei Li, Shiyuan Zhang +7
Data attribution methods aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasing…
cs.LG2024
Efficient Ensembles Improve Training Data Attribution
Junwei Deng, Ting-Wei Li, Shichang Zhang +1
Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such…