发表机构
Arizona State University（亚利桑那州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出Web-CLI架构，将命令行工具等部署为浏览器应用，通过客户端执行实现可验证隐私，展示了四个领域的参考实现，建议其作为处理敏感数据应用的默认架构。
AI 中文摘要
我们推出Web-CLI，这是一种新颖的应用架构，它将强大的计算能力（编译为WebAssembly的命令行工具、通过客户端推理运行时运行的模型以及GPU加速引擎）部署为零安装、具备离线功能的浏览器应用，同时保留了全部底层能力。与需要服务器端处理并将用户数据暴露给第三方的基于Web的替代方案不同，Web-CLI应用完全在客户端执行，通过架构而非策略提供可验证的隐私保证。我们定义了该模式及其四个属性：保真度、渐进式披露、离线优先和零数据外发。我们在不同领域展示了四个参考实现：ffmpeg-webCLI，一款基于FFmpeg构建的浏览器视频编辑器；whisper-webCLI，通过OpenAI Whisper实现的语音转录；chat-webCLI，基于WebLLM的语言模型推理；以及3mf-webCLI，一款用于将3D模型分割成多材料文件以进行物理3D打印的确定性工具。这些实现共同证明，该模式可推广到确定性媒体处理、神经语音识别、LLM推理和具有物理输出的几何处理领域，我们还概述了它如何扩展到以本地语言模型作为命令界面本身的AI原生界面。我们进一步报告了第三方工具独立复用的早期迹象，表明该模式的适用范围超出了其参考实现。我们在性能和功能 parity 方面将主要实现与原生FFmpeg进行了评估，并认为渐进式披露降低了非技术用户的使用门槛。我们认为，对于处理敏感用户数据（医疗、法律、新闻或个人数据）的应用，Web-CLI应成为默认架构，因为它使数据本地化成为可独立验证的技术属性，而非政策承诺。
英文摘要
We introduce the Web-CLI, a novel application architecture deploying powerful computational capabilities (command-line tools compiled to WebAssembly, models run through client-side inference runtimes, and GPU-accelerated engines) as zero-install, offline-capable browser applications that preserve full underlying capability. Unlike web-based alternatives that require server-side processing and expose user data to third parties, Web-CLI applications execute entirely on the client, providing a verifiable privacy guarantee by architecture rather than policy. We define the pattern and its four properties: fidelity, progressive disclosure, offline-first, and zero egress. We present four reference implementations across distinct domains: ffmpeg-webCLI, a browser-based video editor built on FFmpeg; whisper-webCLI, speech transcription via Transformers.js; chat-webCLI, WebLLM-based language model inference; and 3mf-webCLI, a deterministic tool segmenting 3D models into multi-material files for physical 3D printing. Together they demonstrate that the pattern generalizes across deterministic media processing, neural speech recognition, LLM inference, and geometry processing with a physical output, and we outline how it extends to AI-native interfaces in which a local language model becomes the command surface itself. We further report early, anecdotal signs of independent reuse by third-party tools, suggesting the pattern generalizes beyond its reference implementations. We evaluate the primary implementation against native FFmpeg on performance and feature parity, and argue that progressive disclosure lowers the barrier for non-technical users. We argue that for applications processing sensitive user data (medical, legal, journalistic, or personal), the Web-CLI should be the default architecture, as it makes data locality an independently verifiable technical property rather than a policy promise.
