Hiromi Arai

Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory

This work asks how consulting memory during dialogue changes what users go on to say, and thus what the memory comes to reveal, and across four support models, memory raises response quality but also empirical leakage, the share of attribute values correctly inferred from the record, by a margin that widens over sessio...