Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents

• URL: http://arxiv.org/abs/2603.19416v1
• Date: Thu, 19 Mar 2026 19:18:40 GMT
• Title: Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents
• Abstract summary: We investigate in-context, experiential learning by examining how interactions with privacy tools enhance users' privacy learning.<n>We integrate a just-in-time privacy notice panel into ChatGPT's interface which we simulated.<n>We qualitatively analyzed participants' perceptions of privacy before and after the task sessions and interface design features that supported or hindered user-led protection of sensitive information.
• Score: 0.1390311627586184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supporting users in protecting sensitive information when using conversational agents (CAs) is crucial, as users may undervalue privacy protection due to outdated, partial, or inaccurate knowledge about privacy in CAs. Although privacy knowledge can be developed through standalone resources, it may not readily translate into practice and may remain detached from real-time contexts of use. In this study, we investigate in-context, experiential learning by examining how interactions with privacy tools during chatbot use enhance users' privacy learning. We also explore interface design features that facilitate engagement with these tools and learning about privacy by simulating ChatGPT's interface which we integrated with a just-in-time privacy notice panel. The panel intercepts messages containing sensitive information, warns users about potential sensitivity, offers protective actions, and provides FAQs about privacy in CAs. Participants used versions of the chatbot with and without the privacy panel across two task sessions designed to approximate realistic chatbot use. We qualitatively analyzed participants' pre- and post-test survey responses and think-aloud transcripts and describe findings related to (a) participants' perceptions of privacy before and after the task sessions and (b) interface design features that supported or hindered user-led protection of sensitive information. Finally, we discuss future directions for designing user-facing privacy tools in CAs that promote privacy learning and user engagement in protecting privacy in CAs.

Related papers

• PromptPET: Privacy-Utility Optimized Prompt Obfuscation [6.5675177002666665]
  We aim to protect user privacy via a user-side mechanism that transforms sensitive information in a user prompt.<n>This approach faces an inherent tradeoff between protecting privacy and preserving utility.<n>We introduce PROMPTPET, an agent that selects the best obfuscation action for each sensitive part of the prompt.
  arXiv  Detail & Related papers  (2026-07-03T03:59:34Z)
• Understanding Users' Privacy Reasoning and Behaviors During Chatbot Use to Support Meaningful Agency in Privacy [0.1390311627586184]
  We examined students' in-the-moment disclosure and protection behaviors, as well as the reasoning underlying these behaviors.<n>Participants used a simulated ChatGPT interface with and without a privacy notice panel that intercepts message submissions.<n>We analyzed how the panel fostered privacy awareness, encouraged protective actions, and supported context-specific reasoning about what information to protect and how.
  arXiv  Detail & Related papers  (2026-01-26T04:13:45Z)
• Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents [33.26308626066122]
  We characterize the notion of contextual privacy for user interactions with Conversational Agents (LCAs)<n>It aims to minimize privacy risks by ensuring that users (sender) disclose only information that is both relevant and necessary for achieving their intended goals.<n>We propose a locally deployable framework that operates between users and LCAs, identifying and reformulating out-of-context information in user prompts.
  arXiv  Detail & Related papers  (2025-02-22T09:05:39Z)
• PRISMe: A Novel LLM-Powered Tool for Interactive Privacy Policy Assessment [0.6554326244334868]
  We present PRISMe, a novel Large Language Model (LLM)-driven privacy policy assessment tool.<n>The tool helps users to understand the essence of a lengthy, complex privacy policy while browsing.<n>We evaluate PRISMe's efficiency, usability, understandability of the provided information, and impacts on awareness.
  arXiv  Detail & Related papers  (2025-01-27T13:27:04Z)
• On the Differential Privacy and Interactivity of Privacy Sandbox Reports [78.85958224681858]
  The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities.<n>We provide an abstract model for analyzing the privacy of these APIs and show that they satisfy a formal DP guarantee.
  arXiv  Detail & Related papers  (2024-12-22T08:22:57Z)
• Inference Privacy: Properties and Mechanisms [8.471466670802817]
  Inference Privacy (IP) can allow a user to interact with a model while providing a rigorous privacy guarantee for the users' data at inference.<n>We present two types of mechanisms for achieving IP: namely, input perturbations and output perturbations which are customizable by the users.
  arXiv  Detail & Related papers  (2024-11-27T20:47:28Z)
• 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)
• NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human [56.46355425175232]
  We suggest sanitizing sensitive text using two common strategies used by humans.<n>We curate the first corpus, coined NAP2, through both crowdsourcing and the use of large language models.<n>Compared to the prior works on anonymization, the human-inspired approaches result in more natural rewrites.
  arXiv  Detail & Related papers  (2024-06-06T05:07:44Z)
• ChatGPT for Us: Preserving Data Privacy in ChatGPT via Dialogue Text Ambiguation to Expand Mental Health Care Delivery [52.73936514734762]
  ChatGPT has gained popularity for its ability to generate human-like dialogue. Data-sensitive domains face challenges in using ChatGPT due to privacy and data-ownership concerns. We propose a text ambiguation framework that preserves user privacy.
  arXiv  Detail & Related papers  (2023-05-19T02:09:52Z)
• Privacy Explanations - A Means to End-User Trust [64.7066037969487]
  We looked into how explainability might help to tackle this problem. We created privacy explanations that aim to help to clarify to end users why and for what purposes specific data is required. Our findings reveal that privacy explanations can be an important step towards increasing trust in software systems.
  arXiv  Detail & Related papers  (2022-10-18T09:30:37Z)

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.