TAICO September 2024 Meetup @Adaptavist

The TAICO team is proud to announce our second meetup on September 17th, 2024 at the Adaptavist office in Toronto. Much thanks to Adaptavist for hosting!

tldr - event registration link - Meetup.com

Registration and Event Details

Please note that we are using Meetup.com for event registration and you must register through that link to attend. Seating is limited so please register early. Thank you and see you there!

Event registration link - Meetup.com

Our goal is to bring artificial intelligence and cybersecurity together. To do that, we need to explore what’s happening in AI and what’s happening in cybersecurity, and where the two intersect and collide. We’re also working to understand how we solve problems in these areas, what that looks like, and how Canada can and will participate.

With that in mind, we’re pleased to announce our speaker and the agenda for our second meeting!

Agenda

• Welcome and introductions
• Demo of GenAI and security in action
• Speaker: Andrei Betlen, Co-Founder and CEO at Patagona Technologies. Andrei is also the principal maintainer of the Llama CPP Python project!
  • Talk: “From Autocomplete to Agents: Leveraging Open Source Tools for Secure GenAI Workloads”
  • Abstract

  The talk will discuss various open source tools projects that close the gap for secure on-prem AI workloads. We’ll also discuss best practices and considerations for developing secure AI systems.

• Speaker: Kellman Meghu, Principal Security Architect at Deepcove
  • Talk: “Safeguarding sensitive data in the era of LLMs”

  • Abstract

    Personally and professionally we are challenged to protect sensitive data from an onslaught of Large Language Models on our phones, hidden in websites and apps, and soon as a part of the Operating System. To what extent can we afford to let LLM’s ingest and learn from our most sensitive data? There are customer loyalty, legal, financial and even political ramifications of information leaking out. At the same time, we can’t put a stranglehold on new innovations that make us and our organizations more effective. I don’t pretend to have all the answers and I don’t think the industry does yet either. This talk is less about using LLMs for better security and more about solving the security issues LLMs create. Expect some philosophy, planning and vision, with pointers to a range of technology solutions. After working with LLM focused teams to build private models; tested private and public training, my organization is cautiously moving forward, not because we feel we have good answers, but because we have no choice in the matter. So here are the challenges I have had (so far) and will discuss openly where I think this is all going.

    • How do I make the thing, that by design is supposed to answer all questions, keep a secret? Will there be secrets?
    • Across data, application, identity and so on, what are some considerations at different points of exploitation and remediation regarding the use of LLMs?
    • New startups are applying LLMs to solve problems with LLMs, what could possibly go wrong? Let’s discuss…

• Lightning talks and demos
• Networking and drinks

Lightning Talks and Demos

Please reach out to us if you’d like to present at the meetup. We are looking for people to talk about what they are working on, what they are building and learning, and are open to any level of experience and technical depth. Whether you are a beginner or an expert, we want to hear from you! We’re all just out here building and learning.

See You There!

Thanks, and we look forward to seeing you there!