作者
Seong Joon Oh, Bernt Schiele, Mario Fritz
发表日期
2019
期刊
Explainable AI: interpreting, explaining and visualizing deep learning
页码范围
121-144
出版商
Springer International Publishing
简介
Much progress in interpretable AI is built around scenarios where the user, one who interprets the model, has a full ownership of the model to be diagnosed. The user either owns the training data and computing resources to train an interpretable model herself or owns a full access to an already trained model to be interpreted post-hoc. In this chapter, we consider a less investigated scenario of diagnosing black-box neural networks, where the user can only send queries and read off outputs. Black-box access is a common deployment mode for many public and commercial models, since internal details, such as architecture, optimisation procedure, and training data, can be proprietary and aggravate their vulnerability to attacks like adversarial examples. We propose a method for exposing internals of black-box models and show that the method is surprisingly effective at inferring a diverse set of internal information …
学术搜索中的文章
SJ Oh, B Schiele, M Fritz - Explainable AI: interpreting, explaining and visualizing …, 2019
SJ Oh, M Augustin, B Schiele, M Fritz - 2017