Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective

Autor: Zhao, Ningsheng, Yu, Jia Yuan, Dzieciolowski, Krzysztof, Bui, Trang

Shapley value attribution (SVA) is an increasingly popular explainable AI (XAI) method, which quantifies the contribution of each feature to the model's output. However, recent work has shown that most existing methods to implement SVAs have some dra

Externí odkaz: http://arxiv.org/abs/2404.13522

Coverless Information Hiding Method Based on Multi-keywords.

Autor: Zhou, Zhili, Mu, Yan, Zhao, Ningsheng, Wu, Q. M. Jonathan, Yang, Ching-Nung

Publikováno v: Cloud Computing & Security: Second International Conference, ICCCS 2016, Nanjing, China, July 29-31, 2016, Revised Selected Papers, Part I; 2016, p39-47, 9p