What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents

• URL: http://arxiv.org/abs/2608.16551v1
• Date: Mon, 17 Aug 2026 13:23:39 GMT
• Title: What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents
• Abstract summary: Long-term memory enables personalized conversational agents to retain user information across sessions.<n>Existing memory architectures primarily optimize for utility while neglecting the risks of unnecessarily storing and reusing private attributes such as personally identifiable information (PII)<n>We introduce Sanitized Privacy-Mapped Memory (SP-Mem), a privacy-aware memory architecture that decouples memory utility from exact private-value exposure.
• Score: 24.32447231758722
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-term memory enables personalized conversational agents to retain user information across sessions. However, existing memory architectures primarily optimize for utility while neglecting the risks of unnecessarily storing and reusing private attributes such as personally identifiable information (PII). Addressing privacy risks in personalized memory is challenging because simply removing sensitive values can undermine system utility. Therefore, privacy protection for memory agents should govern the full life cycle of sensitive values rather than only sanitizing individual records. To address this gap, we introduce Sanitized Privacy-Mapped Memory (SP-Mem), a privacy-aware memory architecture that decouples memory utility from exact private-value exposure. SP-Mem provides a full life-cycle privacy design that identifies and separates sensitive information from raw user inputs, stores sanitized content and exact private values in isolated structures, and selectively retrieves private values based on task requirements and user consent. We further introduce a privacy-aware memory benchmark that jointly evaluates response quality, privacy behavior, and inference cost. Extensive experiments across multiple LLM-based agents show that SP-Mem achieves stronger personalization while reducing unnecessary privacy exposure. Code and data are available at https://github.com/Jensassss/SP-Mem.

Related papers

• MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents [58.65181747637314]
  We propose MemPrivacy, which identifies privacy-sensitive spans on edge devices.<n>It replaces them with semantically structured type-aware placeholders for cloud-side memory processing.<n>MemPrivacy minimizes sensitive data exposure while retaining the information required for effective memory formation and retrieval.
  arXiv  Detail & Related papers  (2026-05-10T13:31:58Z)
• Privacy Amplification by Missing Data [4.9024539661445825]
  We analyze missing data as a privacy amplification mechanism within the framework of differential privacy.<n>We show, for the first time, that incomplete data can yield privacy amplification for differentially private algorithms.
  arXiv  Detail & Related papers  (2026-02-02T10:28:41Z)
• Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning [26.034865955638864]
  We propose a privacy-enhanced continual learning framework that forgets what's sensitive and remembers what matters.<n>Our approach first introduces a token-level dynamic Differential Privacy strategy.<n>Second, we integrate a privacy-guided memory sculpting module.
  arXiv  Detail & Related papers  (2025-09-16T11:01:59Z)
• Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy [64.32494202656801]
  Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence.<n>We present anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context.<n>We also proposeMaskDP to protect non-anonymized but privacy sensitive background information.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration [20.05248442344211]
  PrivacyRestore is a plug-and-play method to protect the privacy of user inputs during inference.<n>We create three datasets, covering medical and legal domains, to evaluate the effectiveness of PrivacyRestore.
  arXiv  Detail & Related papers  (2024-06-03T14:57:39Z)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)
• Algorithms with More Granular Differential Privacy Guarantees [65.3684804101664]
  We consider partial differential privacy (DP), which allows quantifying the privacy guarantee on a per-attribute basis. In this work, we study several basic data analysis and learning tasks, and design algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person.
  arXiv  Detail & Related papers  (2022-09-08T22:43:50Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.