XIAO, Yaxin; YE, Qingqing; LIANG, Zi; LI, Haoyang; LI, RongHua; ZHENG, Huadi; HU, Haibo. Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 42, p. 35903–35912, 2026. DOI: 10.1609/aaai.v40i42.40905. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40905. Acesso em: 14 may. 2026.