PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations

T1Covered by 1 source · first reported by arXiv at 25 Sept, 04:00 UTC

arXiv:2609.30094v1 Announce Type: new Abstract: Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sensitive information during an active conversation, that information may remain behaviorally…

aiscience

Sources

• T1PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM ConversationsarXiv25 Sept, 04:00