[论文解读] Structured access: an emerging paradigm for safe AI deployment

Toby Shevlane|arXiv (Cornell University)|Jan 13, 2022

Adversarial Robustness in Machine Learning被引用 8

一句话总结

本文提出‘结构化访问’作为一种新的安全部署AI范式，通过受控的云端接口限制用户交互，而非开放发布模型和代码。该方法主张通过阻止逆向工程和未经授权的修改来限制滥用，相较于仅关注信息共享的传统发布规范，提供更有效的安全策略。

ABSTRACT

Structured access 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. Structured access 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. Structured access 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 structured access 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.

研究动机与目标

• 解决日益增长的危险AI能力因开放权重模型和代码而广泛可访问的风险。
• 提出从以信息为中心的发布规范转向以工具为中心的AI部署模式。
• 展示基于云端的受限接口如何在保留有益访问的同时防止滥用。
• 确立结构化访问作为AI机构和技术安全措施的可行框架。

提出的方法

• 提出从开放发布AI模型和代码转向通过应用程序编程接口（API）实现受控的云端托管访问。
• 强调云端部署可实现更强的访问控制，并降低逆向工程或未经授权修改的风险。
• 引入‘远距离交互’的概念，即用户与AI系统交互而不直接接触其内部架构。
• 倡导建立支持结构化访问的制度框架，包括治理和合规机制。
• 将结构化访问定位为对现有发布规范的补充，重点在于AI系统的工具性特征，而非其信息内容。
• 强调技术和组织控制在AI部署过程中维持安全的重要性。

实验结果

研究问题

• RQ1 AI开发者如何在不限制有益访问的前提下防止强大AI系统的滥用？
• RQ2 当前发布规范在控制AI风险方面存在哪些局限性？
• RQ3 基于云端的受限接口能否有效防止AI系统的逆向工程和未经授权修改？
• RQ4 与开放权重模型分发相比，结构化访问在安全性和实用性方面有何差异？
• RQ5 支持结构化访问广泛采用所需的技术和制度框架是什么？

主要发现

• 结构化访问通过限制对模型权重和内部机制的直接访问，降低了滥用风险。
• 云端部署可更强地执行使用政策，并检测恶意行为。
• 通过API限制访问可防止用户修改或逆向工程AI系统。
• 该方法保留了对合法、安全使用场景的AI能力访问。
• 已有结构化访问的早期实例，但其技术接口和制度治理仍需进一步发展。
• 对于高度强大的AI系统，结构化访问相比仅控制信息而言，提供了更稳健的安全策略。