arXiv cs.CY· Will Tucker-Ray, Marika Swanberg, Alexander Knop, Marvin Chow, Eric Culbertson, Julian Jacobs, Pritish Kamath, Ravi Kumar, Jason Mothersill, Mikhail Pravilov, Eugene Quan, Yurii Sushko·· 11 小时前AI 评分31
Gemini Nano Banana 图像生成与编辑的病毒式传播、教育与商业用途有何不同？一项隐私保护描述性分析
How are viral trends different from educational and commercial uses of LLM image generation and editing? A privacy-preserving descriptive analysis
AI 导读
研究利用 Google 开发的 Urania 框架，在差分隐私（DP）保障下分析了 2026 年初使用 Gemini Nano Banana 模型的 210 万段对话，全程不查看任何单张图像或单条提示词。
正文 · 原文
Authors:Will Tucker-Ray, Marika Swanberg, Alexander Knop, Marvin Chow, Eric Culbertson, Julian Jacobs, Pritish Kamath, Ravi Kumar, Jason Mothersill, Mikhail Pravilov, Eugene Quan, Yurii Sushko
Abstract:Gemini's Nano Banana models, first introduced in late 2025, led to a shift in the capabilities and use of image generation and editing. We utilize Urania, a Google-developed framework for generating insights about LLM chatbot interactions with rigorous differential privacy (DP) guarantees, to analyze use cases and intents, techniques and ways of prompting, without ever looking at a single image or individual prompt. We select a subsample of 2.1M conversations in early 2026 which utilized Nano Banana models, into roughly 800 clusters in five categories: (1) Social & Viral Sharing, (2) Brand & Marketing Collateral, (3) Educational & Technical Information Media, (4) Product Visualizations & E-commerce, and (5) Architectural & Spatial Designs. We then compare these clusters on 21 features of use, measuring aspects of prompts' (a) editing techniques, (b) artistic style requests, (c) composition, and (d) chatbot interactions. This allows us to describe a baseline of how people are using image generation and editing tools for different use cases---(including growing and emergent use cases which were not possible before Nano Banana)---in a privacy-preserving manner.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.08749 [cs.CY] |
| (or arXiv:2611.08749v1 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08749 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marika Swanberg [view email]
[v1]
Thu, 5 Nov 2026 21:56:29 UTC (6,049 KB)
来源：arXiv cs.CY · arxiv.org