# MemTrust: A Zero-Trust Architecture for Unified AI Memory System

arXiv: https://arxiv.org/abs/2601.07004 · HTML: https://mlsanity.com/paper/2601.07004/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 11 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Machine Learning with Confidential Computing: A Systematization of Knowledge](https://mlsanity.com/paper/2208.10134/) (2022)
- [Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study](https://mlsanity.com/paper/2409.03992/) (2024)

## Built on by (most cited first, 3 of 3)

- [Opal: Private Memory for Personal AI](https://mlsanity.com/paper/2604.02522/) (2026)
- [Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases](https://mlsanity.com/paper/2606.18497/) (2026)
- [The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI](https://mlsanity.com/paper/2607.19433/) (2026)

## Abstract (arXiv)

AI memory systems are evolving toward unified context layers that enable efficient cross-agent collaboration and multi-tool workflows, facilitating better accumulation of personal data and learning of user preferences. However, centralization creates a trust crisis where users must entrust cloud providers with sensitive digital memory data. We identify a core tension between personalization demands and data sovereignty: centralized memory systems enable efficient cross-agent collaboration but expose users' sensitive data to cloud provider risks, while private deployments provide security but limit collaboration. To resolve this tension, we aim to achieve local-equivalent security while enabling superior maintenance efficiency and collaborative capabilities. We propose a five-layer architecture abstracting common functional components of AI memory systems: Storage, Extraction, Learning, Retrieval, and Governance. By applying TEE protection to each layer, we establish a trustworthy framework. Based on this, we design MemTrust, a hardware-backed zero-trust architecture that provides cryptographic guarantees across all layers. Our contributions include the five-layer abstraction, "Context from MemTrust" protocol for cross-application sharing, side-channel hardened retrieval with obfuscated access patterns, and comprehensive security analysis. The architecture enables third-party developers to port existing systems with acceptable development costs, achieving system-wide trustworthiness. We believe that AI memory plays a crucial role in enhancing the efficiency and collaboration of agents and AI tools. AI memory will become the foundational infrastructure for AI agents, and MemTrust serves as a universal trusted framework for AI memory systems, with the goal of becoming the infrastructure of memory infrastructure.