From Identifiers to Inference Reconstructive Identity, Cross-Modal Linkage, and the Collapse of Practical Obscurity in AI Systems
Summary
This paper examines how AI systems can leverage identifiers to infer and reconstruct identities through cross-modal linkage, leading to a collapse in practical obscurity and raising significant privacy concerns.
Similar Articles
Identity from the Outside: A Conceptual Framework and Research Program for AI Personality Clones
This arXiv preprint proposes a conceptual framework and research program for AI personality clones, operationalizing identity through observable manifestations and outlining experimental designs for evaluating clone fidelity.
RealityTest: How People Probe AI Identity and Whether Models Disclose It
This paper introduces RealityTest, a multimodal, multilingual benchmark to evaluate whether AI systems disclose their identity when probed by users, based on real human queries collected across 49 countries. It finds that only 31% of people ask directly about identity, and that human questions are more diverse than synthetic ones, revealing that phrasing and context matter more for disclosure than the specific model.
Is “AI identity” becoming a separate problem from human identity?
The article explores whether AI agents operating independently online will require separate identity frameworks for humans, organizations, and AI, with different rules and trust models, questioning if this separation is necessary.
Recently wrote arguing that AI should have to identify itself as such. Would love the communities feedback!
Argues for legally requiring AI to disclose its non-human nature when interacting with people, citing Colorado's new law and the broader need for transparency in AI-influenced decisions.
How close are we to AI systems that can reliably verify identity in conversations?
The article explores the challenges of identity verification in conversational AI systems, highlighting risks like impersonation and prompt injection, and questions whether serious approaches are being developed.