Trustworthy AI through AI security

Name: Trustworthy AI through AI security | CISCO
Uploaded: 2026-09-04T15:37:53.000Z
Duration: 1 h 28 min 48 s
Channel: AI for Good
Description: This panel from the AI for Good Global Summit 2026, organized with Cisco, discusses how AI security is essential for trustworthy AI, covering topics like data poisoning, prompt injection, and jailbreaking.

What you'll learn

You learn why AI security is a precondition for trustworthy AI
You discover how data poisoning can undermine AI systems
You see what prompt injection and jailbreaking mean for AI
You learn why AI systems need to be secured by design

Frequently asked questions

Why is security needed to make AI trustworthy?

The panel argues that AI can only be trustworthy if the systems behind it are secure. Trustworthy AI adoption depends on securing AI systems by design across the whole AI stack.

Which AI security threats are covered?

The workshop covers data poisoning, prompt injection and jailbreaking as security risks for AI systems, alongside security and resilience across the AI stack infrastructure.

Where was this workshop recorded?

The workshop was recorded live at the AI for Good Global Summit 2026 at Palexpo in Geneva, Switzerland, and was organized in partnership with Cisco.

Topics

ai-security trustworthy-ai ai-governance cybersecurity ai-summit

In this video

Cisco

Sources

What is known about this topic outside the broadcast, and where it says so.

Description from the channel

Can AI ever be trustworthy if the systems behind it are not secure? Whitney Baird, Matteo Quattrocchi, Igor Minaev, Cosmas Luckyson Zavazava and Cynthia Leungo Lesufi explore security and resilience across the AI stack — from infrastructure and data poisoning to prompt injection and jailbreaking. This workshop organized in partnership with Cisco examines why trustworthy AI adoption depends on securing AI systems by design. Recorded live at the AI for Good Global Summit 2026 at Palexpo in Geneva, Switzerland. _____________________________________________________________________ AI for Good is identifying innovative AI applications, building skills and standards, and advancing partnerships to solve global challenges. AI for Good is organized by ITU in partnership with over 50 UN partners and co-convened with the Government of Switzerland. Join the Neural Network! 👉https://aiforgood.itu.int/neural-network/ The AI for Good networking community platform powered by AI. Designed to help users build connections with innovators and experts, link innovative ideas with social impact opportunities, and bring the community together to solve global challenges using AI. 🔴 Watch the latest #AIforGood videos! https://www.youtube.com/c/AIforGood/videos 📩 Stay updated and join our weekly AI for Good newsletter: http://eepurl.com/gI2kJ5 🗞Check out the latest AI for Good news: https://aiforgood.itu.int/newsroom/ 📱Explore the AI for Good blog: https://aiforgood.itu.int/ai-for-good-blog/ 🌎 Connect on our social media: Website: https://aiforgood.itu.int/ X: https://twitter.com/AIforGood LinkedIn Page: https://www.linkedin.com/company/26511907 LinkedIn Group: https://www.linkedin.com/groups/8567748 Instagram: https://www.instagram.com/aiforgood Facebook: https://www.facebook.com/AIforGood Disclaimer: The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.

Trustworthy AI through AI security | CISCO