评估在线视觉语言模型中的隐私保护与效用
Assessing Privacy Preservation and Utility in Online Vision-Language Models
AI总结：
本文研究了在线视觉语言模型中个人身份信息泄露问题，探讨了图像中上下文关系提取对隐私的影响，并提出保护隐私同时保持效用的方法。
摘要：
随着在线视觉语言模型（OVLMs）在图像处理中的广泛应用，隐私风险显著增加。个体频繁上传图像以获取各种效用，却不知潜在的隐私侵犯风险。图像中包含与个人身份信息（PII）相关的关系，即使看似无害的细节也可能通过周围线索间接揭示敏感信息。本文探讨了上传到OVLMs的图像中PII泄露的关键问题及其对用户隐私的影响。我们研究了从图像中提取上下文关系如何导致直接（显性）或间接（隐性）暴露PII，显著损害个人隐私。此外，我们提出保护隐私的同时保持图像在基于视觉语言模型（VLM）应用中预期效用的方法。我们的评估展示了这些技术的有效性，突显了在在线图像处理环境中维护效用和保护隐私之间的微妙平衡。索引术语-个人身份信息（PII），隐私，效用，隐私问题，敏感信息
英文摘要：
The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently upload images for various utilities, unaware of the potential for privacy violations. Images contain relationships that relate to Personally Identifiable Information (PII), where even seemingly harmless details can indirectly reveal sensitive information through surrounding clues. This paper explores the critical issue of PII disclosure in images uploaded to OVLMs and its implications for user privacy. We investigate how the extraction of contextual relationships from images can lead to direct (explicit) or indirect (implicit) exposure of PII, significantly compromising personal privacy. Furthermore, we propose methods to protect privacy while preserving the intended utility of the images in Vision Language Model (VLM)-based applications. Our evaluation demonstrates the efficacy of these techniques, highlighting the delicate balance between maintaining utility and protecting privacy in online image processing environments. Index Terms-Personally Identifiable Information (PII), Privacy, Utility, privacy concerns, sensitive information
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。
