arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.15044cs.HC
收藏

Adanonymizer:在人机交互中交互式导航并平衡隐私与输出性能的双重性

Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interaction

Shuning Zhang, Xin Yi, Haobin Xing, Lyumanshan Ye, Yongquan Hu, Hewu Li

AI总结:

针对人机交互中隐私与性能难以平衡的问题,提出Adanonymizer匿名化插件,通过权衡曲线和二维调色板界面让用户交互式调整,显著减少修改时间并提升用户偏好。

摘要:

当前的大语言模型(LLMs)无法支持用户在个别咨询中精确平衡隐私保护与输出性能。我们引入了Adanonymizer,一个匿名化插件,允许用户通过导航权衡曲线来控制这种平衡。一项调查(N=221)揭示了隐私悖论,即用户尽管承认隐私风险,却经常泄露敏感信息。该研究进一步表明,隐私风险与模型输出性能并无显著相关性,凸显了导航这种权衡的可能性。Adanonymizer按类型对隐私和效用评分进行归一化,并根据用户偏好自动对敏感术语进行假名化,显著减少了用户工作量。其二维调色板界面可视化了隐私-效用权衡,允许用户通过操作一个点来调整平衡。一项评估(N=36)将Adanonymizer与消融方法和差分隐私技术进行了比较,其中Adanonymizer显著减少了修改时间,获得了更好的感知模型性能和整体用户偏好。

英文摘要:

Current Large Language Models (LLMs) cannot support users to precisely balance privacy protection and output performance during individual consultations. We introduce Adanonymizer, an anonymization plug-in that allows users to control this balance by navigating a trade-off curve. A survey (N=221) revealed a privacy paradox, where users frequently disclosed sensitive information despite acknowledging privacy risks. The study further demonstrated that privacy risks were not significantly correlated with model output performance, highlighting the potential to navigate this trade-off. Adanonymizer normalizes privacy and utility ratings by type and automates the pseudonymization of sensitive terms based on user preferences, significantly reducing user effort. Its 2D color palette interface visualizes the privacy-utility trade-off, allowing users to adjust the balance by manipulating a point. An evaluation (N=36) compared Adanonymizer with ablation methods and differential privacy techniques, where Adanonymizer significantly reduced modification time, achieved better perceived model performance and overall user preference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑