Sattestation 逻辑
A Logic of Sattestation
AI总结:
本文提出 Sattestation 逻辑,用于推理自认证传统地址的上下文信任及标签绑定信任,给出 Kripke 语义、可靠性证明和完备可终止的信任推导算法。
摘要:
我们引入一种用于推理网络地址上下文信任的逻辑,为其提供 Kripke 语义,并在关于主体策略的合理假设下证明其可靠性。自认证传统地址(SATAs)是有效的 DNS 地址或 URL,通常对人类和网络基础设施都有意义,并且在地址本身中包含对公钥的承诺。当前网络地址的信任是通过域名注册、TLS 证书以及互联网基础设施的其他层级元素建立的。SATAs 支持这种结构性的信任根,同时也支持与描述性属性相关联的互补性上下文信任根。现有的结构性信任根使网络连接面临多种有充分记录且严重的劫持漏洞。上下文信任根除其他优点外,还对这些漏洞提供了更强的抵抗力。我们还考虑了带标签的 SATAs,这些标签包含描述性属性,例如某个 SATA 是新闻机构的地址、属于特定政府或公司的站点、包含特定主题信息的站点等。我们的逻辑既处理对地址绑定在一起的身份的信任,也处理对标签与该地址绑定的信任。我们的逻辑允许对指定标签的信任委托、提供更多或更少具体信息的标签之间的关系,以及这两个方面之间的交互进行推理。除了可靠性之外,我们还证明,如果一个主体信任某个特定身份(可能带有标签),那么要么这种信任是最初假定的,要么存在从初始信任假设到该信任的委托信任链。我们还提出了一种算法,能够从初始信任假设集合中有效推导出所有可能的信任陈述,并证明该算法是可靠的、完备的和可终止的。
英文摘要:
We introduce a logic for reasoning about contextual trust for web addresses, provide a Kripke semantics for it, and prove its soundness under reasonable assumptions about principals' policies. Self-Authenticating Traditional Addresses (SATAs) are valid DNS addresses or URLs that are generally meaningful -- to both humans and web infrastructure -- and contain a commitment to a public key in the address itself. Trust in web addresses is currently established via domain name registration, TLS certificates, and other hierarchical elements of the internet infrastructure. SATAs support such structural roots of trust but also complementary contextual roots associated with descriptive properties. The existing structural roots leave web connections open to a variety of well-documented and significant hijack vulnerabilities. Contextual trust roots provide, among other things, stronger resistance to such vulnerabilities. We also consider labeled SATAs, which include descriptive properties such as that a SATA is an address for a news organization, a site belonging to a particular government or company, a site with information about a certain topic, etc. Our logic addresses both trust in the bound together identity of the address and trust in the binding of labels to it. Our logic allows reasoning about delegation of trust with respect to specified labels, relationships between labels that provide more or less specific information, and the interaction between these two aspects. In addition to soundness, we prove that if a principal trusts a particular identity (possibly with label), then either this trust is initially assumed, or there is a trust chain of delegations to this from initial trust assumptions. We also present an algorithm that effectively derives all possible trust statements from the set of initial trust assumptions and show it to be sound, complete, and terminating.
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。