# MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

arXiv: https://arxiv.org/abs/2605.09530 · HTML: https://mlsanity.com/paper/2605.09530/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 10 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 30 of 36)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [Unveiling Privacy Risks in LLM Agent Memory](https://mlsanity.com/paper/2502.13172/) (2025)
- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)
- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data](https://mlsanity.com/paper/2406.14773/) (2024)
- [Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy](https://mlsanity.com/paper/2412.04697/) (2024)
- [Firewalls to Secure Dynamic LLM Agentic Networks](https://mlsanity.com/paper/2502.01822/) (2025)
- [Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Risks](https://mlsanity.com/paper/2310.07879/) (2023)
- [CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs](https://mlsanity.com/paper/2511.14937/) (2025)
- [According to Me: Long-Term Personalized Referential Memory QA](https://mlsanity.com/paper/2603.01990/) (2026)
- [PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI](https://mlsanity.com/paper/2512.24848/) (2025)
- [PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration](https://mlsanity.com/paper/2511.22788/) (2025)
- [LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples](https://mlsanity.com/paper/2512.07375/) (2025)
- [VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy](https://mlsanity.com/paper/2510.04261/) (2025)

## Built on by (most cited first, 7 of 7)

- [MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems](https://mlsanity.com/paper/2605.28732/) (2026)
- [When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills](https://mlsanity.com/paper/2608.03700/) (2026)
- [When Should Models Change Their Minds? Contextual Belief Management in Large Language Models](https://mlsanity.com/paper/2605.30219/) (2026)
- [Exploring Autonomous Agentic Data Engineering for Model Specialization](https://mlsanity.com/paper/2605.30407/) (2026)
- [MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution](https://mlsanity.com/paper/2605.28646/) (2026)
- [Rethinking Memory as Continuously Evolving Connectivity](https://mlsanity.com/paper/2605.28773/) (2026)
- [DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents](https://mlsanity.com/paper/2608.03130/) (2026)

## Abstract (arXiv)

As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user information, while existing privacy protection methods typically rely on aggressive masking that removes task-relevant semantics and consequently degrades memory utility and personalization quality. To address this challenge, We propose MemPrivacy, which identifies privacy-sensitive spans on edge devices, replaces them with semantically structured type-aware placeholders for cloud-side memory processing, and restores the original values locally when needed. By decoupling privacy protection from semantic destruction, MemPrivacy minimizes sensitive data exposure while retaining the information required for effective memory formation and retrieval. We also construct MemPrivacy-Bench for systematic evaluation, a dataset covering 200 users and over 155k privacy instances, and introduce a four-level privacy taxonomy for configurable protection policies. Experiments show that MemPrivacy achieves strong performance in privacy information extraction, substantially surpassing strong general-purpose models such as GPT-5.2 and Gemini-3.1-Pro, while also reducing inference latency. Across multiple widely used memory systems, MemPrivacy limits utility loss to within 1.6%, outperforming baseline masking strategies. Overall, MemPrivacy offers an effective balance between privacy protection and personalized memory utility for edge-cloud agents, enabling secure, practical, and user-transparent deployment.