mlsanityData to 7 Oct 2026

From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Management

arXiv 2602.05016 ↗First posted 4 Feb 2026cs.HC cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Managing one's digital footprint is overwhelming, as it spans multiple platforms and involves countless context-dependent decisions. Recent advances in agentic AI offer ways forward by enabling holistic, contextual privacy-enhancing solutions. Building on this potential, we adopted a ''human-as-the-unit'' perspective and investigated users' cross-context privacy challenges through 12 semi-structured interviews. Results reveal that people rely on ad hoc manual strategies while lacking comprehensive privacy controls, highlighting nine privacy-management challenges across applications, temporal contexts, and relationships. To explore solutions, we generated nine AI agent concepts and evaluated them via a speed-dating survey with 116 US participants. The three highest-ranked concepts were all post-sharing management tools with half or full agent autonomy, with users expressing greater trust in AI accuracy than in their own efforts. Our findings highlight a promising design space where users see AI agents bridging the fragments in privacy management, particularly through automated, comprehensive post-sharing remediation of users' digital footprints.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 138 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

39 of 138 references.

References · 39

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  5. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  6. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 559
  7. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  8. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreakercited by 337
  9. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Modelscited by 167
  10. 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Actioncited by 161
  11. 2025Unveiling Privacy Risks in LLM Agent Memorycited by 99
  12. 2024AirGapAgent: Protecting Privacy-Conscious Conversational Agentscited by 90
27 more
  1. 2023"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agentscited by 60
  2. 2024CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applicationscited by 33
  3. 2020Dark Patterns after the GDPR: Scraping Consent Pop-ups and Demonstrating their Influencecited by 27
  4. 2019(Un)informed Consent: Studying GDPR Consent Notices in the Fieldcited by 23
  5. 2024When LLMs Go Online: The Emerging Threat of Web-Enabled LLMscited by 22
  6. 2025Privacy Auditing of Large Language Modelscited by 22
  7. 2024IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomizationcited by 21
  8. 2024Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbotscited by 16
  9. 2018We Value Your Privacy ... Now Take Some Cookies: Measuring the GDPR's Impact on Web Privacycited by 15
  10. 2024Evaluating LLM-based Personal Information Extraction and Countermeasurescited by 12
  11. 2018Discovering Smart Home Internet of Things Privacy Norms Using Contextual Integritycited by 10
  12. 2025Malicious LLM-Based Conversational AI Makes Users Reveal Personal Informationcited by 10
  13. 2025LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Datacited by 10
  14. 2024Robust Utility-Preserving Text Anonymization Based on Large Language Modelscited by 9
  15. 2024Secret Use of Large Language Model (LLM)cited by 9
  16. 2024Empowering Users in Digital Privacy Management through Interactive LLM-Based Agentscited by 9
  17. 2014Privacy Games: Optimal User-Centric Data Obfuscationcited by 7
  18. 2024The Data Minimization Principle in Machine Learningcited by 7
  19. 2026Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Datasetcited by 6
  20. 2024SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacycited by 5
  21. 2025"You don't need a university degree to comprehend data protection this way": LLM-Powered Interactive Privacy Policy Assessmentcited by 5
  22. 2020Informing the Design of Privacy-Empowering Tools for the Connected Homecited by 3
  23. 2025Privacy in Immersive Extended Reality: Exploring User Perceptions, Concerns, and Coping Strategiescited by 3
  24. 2025Imago Obscura: An Image Privacy AI Co-pilot to Enable Identification and Mitigation of Riskscited by 3
  25. 2025Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharingcited by 3
  26. 2023Augmented Reality's Potential for Identifying and Mitigating Home Privacy Leakscited by 1
  27. 2023HIPAAChecker: The Comprehensive Solution for HIPAA Compliance in Android mHealth Appscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Privacy Guardian Agent: Towards Trustworthy AI Privacy Agents
  2. 2026PrivacyAlign: Contextual Privacy Alignment for LLM Agents
  3. 2026AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
  4. 2024Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent
  5. 2026PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
  6. 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
  7. 2026SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints
  8. 2024Operationalizing Contextual Integrity in Privacy-Conscious Assistants