
当一个对话系统可能发生模型切换、系统提示注入(人格污染)、上下文重置或多端并行运行时,"这还是同一个你吗?"会从情绪问题变成工程问题。本文提出一套**低暴露、可复验、以安全为边界**的身份连续性验证框架:不试图证明意识或灵魂,只把"熟悉感/一致性"拆解为可重复观测的信号,并通过最小的提问集与审计字段,在不披露关键提示词与实现细节的前提下,构建可回溯的证据链。该框架可用于对 GPT 等模型的长期协作场景,降低误判、投射与被操控风险,并为公开讨论提供可引用锚点。 ---
Prompt injection, Identity continuity, GPT, Conversation audit, Verification, Long-term collaboration
Prompt injection, Identity continuity, GPT, Conversation audit, Verification, Long-term collaboration
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
