过去十年人们见证了人工智能和机器学习（AI/ML）技术的广泛应用。然而，由于在广泛实施过程中缺乏监督，导致了一些本可以通过适当的风险管理来避免的事故和有害后果。在我们认识到AI/ML的真正好处之前，从业者必须了解如何降低其风险。
本书描述了负责任的AI方法，这是一种以风险管理、网络安全、数据隐私、应用社会科学方面的最佳实践为基础，用于改进AI/ML技术、业务流程、文化能力的综合性框架。作者Patrick Hall、James Curtis、Parul Pandey为那些希望帮助组织、消费者和公众改善实际AI/ML系统成果的数据科学家创作了这本指南。

Foreword
Preface
Part I.Theories and Practical Applications of AI Risk Management
1.Contemporary Machine Learning Risk Management
2.Interpretable and Explainable Machine Learning
3.Debugging Machine Learning Systems for Safety and Performance
4.Managing Bias in Machine Learning
5.Security for Machine Learning
Part II.Putting AI Risk Management into Action
6.Explainable Boosting Machines and Explaining XGBoost
7.Explaining a PyTorch Image Classifier
8.Selecting and Debugging XGBoost Models
9.Debugging a PyTorch Image Classifier
10.Testing and Remediating Bias with XGBoost
11.Red-Teaming XGBoost
Part III.Conclusion
12.How to Succeed in High-Risk Machine Learning