From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents

ArXi:2603.18382v1 Announce Type: new Anonymization is widely treated as a practical safeguard because re-identifying anonymous records was historically costly, requiring domain expertise, tailored algorithms, and manual corroboration. We study a growing privacy risk that may weaken this barrier: LLM-based agents can autonomously reconstruct real-world identities from scattered, individually non-identifying cues. By combining these sparse cues with public information, agents resolve identities without bespoke engineering.