BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Br0nw3n's World - ECPv6.17.4.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://br0nw3n.com
X-WR-CALDESC:Events for Br0nw3n's World
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20260817
DTEND;VALUE=DATE:20260818
DTSTAMP:20260702T231804Z
CREATED:20260702T231710Z
LAST-MODIFIED:20260702T231804Z
UID:27393-1786924800-1787011199@br0nw3n.com
SUMMARY:Antisyphon Training | Keeping Things Local: Build It\, Mesh It\, Lock It
DESCRIPTION:Note: This workshop is still evolving. \nAdditional details and registration links will be added as they become available.\nWhat good is a private AI if you can only use it from the keyboard it runs on? This four hour workshop takes security practitioners past simply installing Ollama and into building something bigger: a locally hosted model your whole team can reach. You’ll customize models for your own workflows\, connect systems over an encrypted mesh network\, and put an authentication layer in front of everything. Because it all runs on hardware you control\, sensitive data never leaves your environment while access expands beyond a single desk. Show up with a laptop that can run two virtual machines\, and walk out with a working private service you built yourself. \n \nWhat You’ll Learn\nBy the end of the workshop\, you will be able to: \n\nInstall and configure Ollama on Linux and manage local models from the command line\nConfigure Ollama to listen on the network so other systems can use it\nCustomize model behavior with Modelfiles to build purpose specific assistants for your workflows\nBuild an encrypted mesh network with Tailscale and connect multiple machines to it\nPut an nginx reverse proxy with basic authentication in front of Ollama to control who can reach it\nExplain the data sovereignty case for local AI and the attack surface you take on when you expose an LLM service\n\nSystem Requirements\nVMware and the lab VMs are provided. Students need a laptop that can run two virtual machines at the same time: \n\n16 GB RAM minimum (24 GB or more recommended)\n60 GB free disk space\nCPU with virtualization support enabled in BIOS/UEFI\nReliable internet connection (required for model downloads and Tailscale)\n\nVM / Lab / Student Information\nVMware and two Linux-based lab VMs will be provided for download before class\, along with import instructions and credentials. Download and import everything ahead of time; model files are large and take time to download and extract. All labs are hands on and build on each other\, ending with a working\, authenticated\, network accessible private AI service. Setting up a free Tailscale account is part of the lab\, so no advance signup is needed. \n \nWho Should Take This Workshop\nSecurity practitioners\, sysadmins\, and technical folks who want AI capability without shipping sensitive data to a third party. If you handle client data\, work under confidentiality constraints\, or just want to know exactly where your prompts go\, this workshop is for you. It is a strong fit for: \n\nRed teamers and penetration testers\, who get a private AI that won’t leak client data during an engagement plus mesh networking they can use on assessments\nConsultants and MSSP staff who handle multiple clients’ sensitive data under contract\nAnyone working in a regulated industry (healthcare\, legal\, finance\, government) where data sovereignty is a compliance requirement\, not a preference\n\nIt is also a fit for anyone who has played with a local model on one machine and wants to turn it into a real service their team can use. \nAudience Skill Level\nIntermediate. You should be comfortable working in a Linux terminal and already know your way around frontier LLMs and basic AI concepts. \nPrerequisites\n\nWorking familiarity with frontier LLMs (ChatGPT\, Claude\, Gemini\, or similar) and basic AI/LLM concepts. You should know what a prompt is\, what a model is\, and what a system prompt does\nComfort with the Linux command line (editing files\, installing packages\, basic troubleshooting)\nComfort running privileged commands (sudo) to install packages and edit system config\nBasic web/HTTP literacy (the idea of clients\, servers\, ports\, and requests)\nBasic familiarity with virtual machines (importing and running a VM in VMware)\nHelpful but not required: familiarity with networking concepts (IP addresses\, ports\, proxies)\nNo prior experience with Ollama\, Tailscale\, or nginx is needed; every tool is introduced from scratch
URL:https://br0nw3n.com/event/antisyphon-training-keeping-things-local-build-it-mesh-it-lock-it/
LOCATION:Online
CATEGORIES:Workshop,Zoom Training
ATTACH;FMTTYPE=image/jpeg:https://br0nw3n.com/wp-content/uploads/AI-Summit-2026-600x338-1.jpg
END:VEVENT
END:VCALENDAR