Rescriber: Smaller-LLM-Powered User-Led Data Minimization for Navigating Privacy Trade-offs in LLM-Based Conversational Agent

• URL: http://arxiv.org/abs/2410.11876v1
• Date: Thu, 10 Oct 2024 01:23:16 GMT
• Title: Rescriber: Smaller-LLM-Powered User-Led Data Minimization for Navigating Privacy Trade-offs in LLM-Based Conversational Agent
• Authors: Jijie Zhou, Eryue Xu, Yaoyao Wu, Tianshi Li,
• Abstract summary: Rescriber is a browser extension that supports user-led data minimization in LLM-based conversational agents. Our studies showed that Rescriber helped users reduce unnecessary disclosure and addressed their privacy concerns. Our findings confirm the viability of smaller-LLM-powered, user-facing, on-device privacy controls.
• Score: 2.2447085410328103
• License:
• Abstract: The proliferation of LLM-based conversational agents has resulted in excessive disclosure of identifiable or sensitive information. However, existing technologies fail to offer perceptible control or account for users' personal preferences about privacy-utility tradeoffs due to the lack of user involvement. To bridge this gap, we designed, built, and evaluated Rescriber, a browser extension that supports user-led data minimization in LLM-based conversational agents by helping users detect and sanitize personal information in their prompts. Our studies (N=12) showed that Rescriber helped users reduce unnecessary disclosure and addressed their privacy concerns. Users' subjective perceptions of the system powered by Llama3-8B were on par with that by GPT-4. The comprehensiveness and consistency of the detection and sanitization emerge as essential factors that affect users' trust and perceived protection. Our findings confirm the viability of smaller-LLM-powered, user-facing, on-device privacy controls, presenting a promising approach to address the privacy and trust challenges of AI.

Related papers

• Can Humans Oversee Agents to Prevent Privacy Leakage? A Study on Privacy Awareness, Preferences, and Trust in Language Model Agents [1.5020330976600738]
  Language model (LM) agents that act on users' behalf for personal tasks can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee the privacy implications of the LM agents.
  arXiv  Detail & Related papers  (2024-11-02T19:15:42Z)
• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• Prompt Tuning as User Inherent Profile Inference Machine [53.78398656789463]
  We propose UserIP-Tuning, which uses prompt-tuning to infer user profiles. A profile quantization codebook bridges the modality gap by profile embeddings into collaborative IDs. Experiments on four public datasets show that UserIP-Tuning outperforms state-of-the-art recommendation algorithms.
  arXiv  Detail & Related papers  (2024-08-13T02:25:46Z)
• 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)
• PriviFy: Designing Tangible Interfaces for Configuring IoT Privacy Preferences [1.4999444543328289]
  We introduce PriviFy, a novel and user-friendly tangible interface that can simplify the configuration of smart devices privacy settings. We envision that positive feedback and user experiences from our study will inspire product developers and smart device manufacturers to incorporate the useful design elements we have identified.
  arXiv  Detail & Related papers  (2024-06-08T12:35:46Z)
• Privacy-Preserving End-to-End Spoken Language Understanding [7.501598786895441]
  Human speech can contain a lot of user-sensitive information, such as gender, identity, and sensitive content. New types of security and privacy breaches have emerged. Users do not want to expose their personal sensitive information to malicious attacks by untrusted third parties. This paper proposes a novel multi-task privacy-preserving model to prevent both the speech recognition (ASR) and identity recognition (IR) attacks.
  arXiv  Detail & Related papers  (2024-03-22T03:41:57Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• "It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents [27.480959048351973]
  The widespread use of Large Language Model (LLM)-based conversational agents (CAs) raises many privacy concerns. We analyzed sensitive disclosures in real-world ChatGPT conversations and conducted semi-structured interviews with 19 LLM-based CA users. We found that users are constantly faced with trade-offs between privacy, utility, and convenience when using LLM-based CAs.
  arXiv  Detail & Related papers  (2023-09-20T21:34:36Z)
• TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection [59.04634695294402]
  Video anomaly detection (VAD) without human monitoring is a complex computer vision task. Privacy leakage in VAD allows models to pick up and amplify unnecessary biases related to people's personal information. We propose TeD-SPAD, a privacy-aware video anomaly detection framework that destroys visual private information in a self-supervised manner.
  arXiv  Detail & Related papers  (2023-08-21T22:42:55Z)
• Tapping into Privacy: A Study of User Preferences and Concerns on Trigger-Action Platforms [0.0]
  The Internet of Things (IoT) devices are rapidly increasing in popularity, with more individuals using Internet-connected devices that continuously monitor their activities. This work explores privacy concerns and expectations of end-users related to Trigger-Action platforms (TAPs) in the context of the Internet of Things (IoT) TAPs allow users to customize their smart environments by creating rules that trigger actions based on specific events or conditions.
  arXiv  Detail & Related papers  (2023-08-11T14:25:01Z)
• 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.