按年被提到
20242024 · 2 次2026
AI 安全、伦理与社会影响›提示注入与对齐风险·arXiv:2408.13247 · cs.CR

An In-Depth Investigation of Data Collection in LLM App Ecosystems

Yuhao Wu, Evin Jaff, Ke Yang, Ning Zhang, Umar Iqbal · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-08-31 · 最近 2024-09-01
2不同的人
2活跃月份
2讨论串
14被引(OpenAlex)
arXiv 摘要(候选层不写导读)

LLM app (tool) ecosystems are rapidly evolving to support sophisticated use cases that often require extensive user data collection. Given that LLM apps are developed by third parties and anecdotal evidence indicating inconsistent enforcement of policies by LLM platforms, sharing user data with these apps presents significant privacy risks. In this paper, we aim to bring transparency in data practices of LLM app ecosystems. We examine OpenAI's GPT app ecosystem as a case study. We propose an LLM-based framework to analyze the natural language specifications of GPT Actions (custom tools) and assess their data collection practices. Our analysis reveals that Actions collect excessive data across 24 categories and 145 data types, with third-party Actions collecting 6.03% more data on average. We find that several Actions violate OpenAI's policies by collecting sensitive information, such as passwords, which is explicitly prohibited by OpenAI. Lastly, we develop an LLM-based privacy policy analysis framework to automatically check the consistency of data collection by Actions with disclosures in their privacy policies. Our measurements indicate that the disclosures for most of the collected data types are omitted, with only 5.8% of Actions clearly disclosing their data collection practices.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次