Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases

ICLR 2026 Conference Submission15537 Authors

Keywords: security and privacy, privacy-preserving framework, homomorphic encryption

TL;DR: We propose a privacy-preserving LLM interaction framework that offloads reasoning to powerful but untrusted LLMs and stores private data via homomorphically encrypted vector databases.

Abstract: Large language models (LLMs) are increasingly used as personal agents, accessing sensitive user data such as calendars, emails, and medical records. Users currently face a trade-off: They can send private records—many of which are stored in remote databases—to powerful but untrusted LLM providers, increasing their exposure risk. Alternatively, they can run less powerful models locally on trusted devices. We bridge this gap: Our Socratic Chain-of-Thought Reasoning first sends a generic user query to a powerful, untrusted LLM, which generates a Chain-of-Thought (CoT) prompt and detailed sub-queries without accessing user data. Next, we embed these sub-queries and perform encrypted sub-second semantic search using our Homomorphically Encrypted Vector Database across one million entries of a single user's private data. This represents a realistic scale of personal documents, emails, and records accumulated over years of digital activity. Finally, we feed the CoT prompt and the decrypted records to a local language model and generate the final response. On the LoCoMo long-context QA benchmark, our hybrid framework—combining GPT-4o with a local Llama-3.2-1B model—outperforms using GPT-4o alone by up to 7.1 percentage points. This demonstrates a first step toward systems where tasks are decomposed and split between untrusted strong LLMs and weak local ones, preserving user privacy.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 15537