arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03689cs.CY
收藏

通过分布式账本技术实现安全的通用人工智能

Safe Artificial General Intelligence via Distributed Ledger Technology

Kristen W. Carlson

AI总结:

针对AGI安全性与价值对齐难题,提出基于分布式账本技术的11条充要公理,借助区块链、智能合约、去中心化应用等实现防黑客、审计追踪、组件管控等功能,保障AGI不危害人类且与人类价值对齐。

摘要:

研究背景:专家观察人士与人工智能(AI)发展指标显示,未来几十年内AI将超越人类智能水平。能力超越人类的通用人工智能(AGI)究竟会成为史上最大福祉还是一场灾难,目前尚无定论。既没有证据表明AGI必将造福人类,也没有证据证明AGI不会伤害甚至消灭人类。研究目标:本文提出一套逻辑上相互独立的概念组件,它们是实现以下两个目标的充要条件:1)确保大多数已知AGI场景不会危害人类;2)使AGI的价值观与目标和人类价值观实现稳健对齐。研究方法:通过系统梳理恶意AI产生的每一类路径,我们可以推导出应对该类路径所需的方法/公理。结果与讨论:分布式账本技术(DLT,即区块链)是本方案不可或缺的组成部分,例如它可降低被黑客攻击的概率,提供审计追踪以检测并纠正错误,或识别导致漏洞或故障的组件并远程和/或自动将其替换或关停,还可通过去中心化应用(dApps)分离并平衡AGI的核心组件。基于DLT的智能合约是应对AI演化速度过快、人类无法监测与干预这一问题的必要手段。本文提出的公理包括:1)通过市场许可获取技术使用权;2)体现在DLT中的透明伦理准则;3)通过DLT加密的道德规范;4)以价值观(伦理)为根基的行为控制结构;5)所有关键组件的独立条形码标识;6)配置项(源自业务连续性/灾难恢复规划);7)通过DLT保障的身份验证;8)基于DLT的智能自动化合约;9)去中心化应用——通过DLT加密的AI软件代码模块;10)通过DLT存储的组件使用审计追踪;11)由DLT请愿机制强化的社会排斥(剥夺社会资源)。

英文摘要:

Background. Expert observers and artificial intelligence (AI) progression metrics indicate AI will exceed human intelligence within a few decades. Whether general AI that exceeds human capabilities (AGI) will be the single greatest boon in history or a disaster is unknown. No proofs exist that AGI will benefit humans or that AGI will not harm or eliminate humans. Objective. I propose a set of logically distinct conceptual components that are necessary and sufficient to 1) ensure that most known AGI scenarios will not harm humanity and 2) robustly align AGI values and goals with human values. Methods. By systematically addressing each pathway category to malevolent AI we can induce the methods/axioms required to redress the category. Results and Discussion. Distributed ledger technology (DLT, blockchain) is integral to this proposal, e.g. to reduce the probability of hacking, provide an audit trail to detect and correct errors or identify components causing vulnerability or failure and replace them or shut them down remotely and/or automatically, and to separate and balance key AGI components via decentralized apps (dApps). Smart contracts based on DLT are necessary to address evolution of AI that will be too fast for human monitoring and intervention. The proposed axioms. 1) Access to technology by market license. 2) Transparent ethics embodied in DLT. 3) Morality encrypted via DLT. 4) Behavior control structure with values (ethics) at roots. 5) Individual bar-code identification of all critical components. 6) Configuration Item (from business continuity/disaster recovery planning). 7) Identity verification secured via DLT. 8) Smart automated contracts based on DLT. 9) Decentralized applications - AI software code modules encrypted via DLT. 10) Audit trail of component usage stored via DLT. 11) Social ostracism (denial of societal resources) augmented by DLT petitions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑