Structured access to AI capabilities: an emerging paradigm for safe AI deployment

by   Toby Shevlane, et al.

Structured capability access ("SCA") is an emerging paradigm for the safe deployment of artificial intelligence (AI). Instead of openly disseminating AI systems, developers facilitate controlled, arm's length interactions with their AI systems. The aim is to prevent dangerous AI capabilities from being widely accessible, whilst preserving access to AI capabilities that can be used safely. The developer must both restrict how the AI system can be used, and prevent the user from circumventing these restrictions through modification or reverse engineering of the AI system. SCA is most effective when implemented through cloud-based AI services, rather than disseminating AI software that runs locally on users' hardware. Cloud-based interfaces provide the AI developer greater scope for controlling how the AI system is used, and for protecting against unauthorized modifications to the system's design. This chapter expands the discussion of "publication norms" in the AI community, which to date has focused on the question of how the informational content of AI research projects should be disseminated (e.g., code and models). Although this is an important question, there are limits to what can be achieved through the control of information flows. SCA views AI software not only as information that can be shared but also as a tool with which users can have arm's length interactions. There are early examples of SCA being practiced by AI developers, but there is much room for further development, both in the functionality of cloud-based interfaces and in the wider institutional framework.


page 1

page 2

page 3

page 4


Designer-User Communication for XAI: An epistemological approach to discuss XAI design

Artificial Intelligence is becoming part of any technology we use nowada...

Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?

Artificial intelligence (AI) systems will increasingly be used to cause ...

Choose, not Hoard: Information-to-Model Matching for Artificial Intelligence in O-RAN

Open Radio Access Network (O-RAN) is an emerging paradigm, whereby virtu...

Toward Next Generation Open Radio Access Network–What O-RAN Can and Cannot Do!

The open radio access network (O-RAN) describes an industry-driven open ...

Development of Authenticated Clients and Applications for ICICLE CI Services – Final Report for the REHS Program, June-August, 2022

The Artificial Intelligence (AI) institute for Intelligent Cyberinfrastr...

Participation Interfaces for Human-Centered AI

Emerging artificial intelligence (AI) applications often balance the pre...

Flows: Building Blocks of Reasoning and Collaborating AI

Recent advances in artificial intelligence (AI) have produced highly cap...

Please sign up or login with your details

Forgot password? Click here to reset