Problems of AI safety are the subject of increasing interest for engineers and policymakers alike. This brief uses the CSET Map of Science to investigate how research into three areas of AI safety — robustness, interpretability and reward learning — is progressing. It identifies eight research clusters that contain a significant amount of research relating to these three areas and describes trends and key papers for each of them.

​​This Classifying AI Systems Interactive presents several AI system classification frameworks developed to distill AI systems into concise, comparable and policy-relevant dimensions. It provides key takeaways and framework-specific results from CSET’s analysis of more than 1,800 system classifications done by survey respondents using the frameworks. You can explore the frameworks and example AI systems used in the survey, and even take the survey.

This paper is the fourth installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” outlined three categories of AI safety issues—problems of robustness, assurance, and specification—and the subsequent two papers described problems of robustness and assurance, respectively. This paper introduces specification as a key element in designing modern machine learning systems that operate as intended.

This brief explores the development and testing of artificial intelligence system classification frameworks intended to distill AI systems into concise, comparable and policy-relevant dimensions. Comparing more than 1,800 system classifications, it points to several factors that increase the utility of a framework for human classification of AI systems and enable AI system management, risk assessment and governance.

As modern machine learning systems become more widely used, the potential costs of malfunctions grow. This policy brief describes how trends we already see today—both in newly deployed artificial intelligence systems and in older technologies—show how damaging the AI accidents of the future could be. It describes a wide range of hypothetical but realistic scenarios to illustrate the risks of AI accidents and offers concrete policy suggestions to reduce these risks.

China wants to be a “cyber powerhouse” (网络强国). At the heart of this mission is the sprawling 40 km2 campus of the National Cybersecurity Center. Formally called the National Cybersecurity Talent and Innovation Base (国家网络安全人才与创新基地), the NCC is being built in Wuhan. The campus, which China began constructing in 2017 and is still building, includes seven centers for research, talent cultivation, and entrepreneurship; two government-focused laboratories; and a National Cybersecurity School.

This paper is the third installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” described three categories of AI safety issues: problems of robustness, assurance, and specification. This paper introduces interpretability as a means to enable assurance in modern machine learning systems.

This paper is the second installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” described three categories of AI safety issues: problems of robustness, assurance, and specification. This paper introduces adversarial examples, a major challenge to robustness in modern machine learning systems.

This paper is the first installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. In it, the authors introduce three categories of AI safety issues: problems of robustness, assurance, and specification. Other papers in this series elaborate on these and further key concepts.

The rapid integration of artificial intelligence into military systems raises critical questions of ethics, design and safety. While many states and organizations have called for some form of “AI arms control,” few have discussed the technical details of verifying countries’ compliance with these regulations. This brief offers a starting point, defining the goals of “AI verification” and proposing several mechanisms to support arms inspections and continuous verification.