Securing AI: Threat Modeling & Detection

Securing AI: Threat Modeling & Detection

Is Artificial Intelligence the ultimate security dragon, we need to slay, or a powerful ally we must train? Recorded LIVE at BSidesSF, this special episode dives headfirst into the most pressing debates around AI security.

Join host Ashish Rajan as he navigates the complex landscape of AI threats and opportunities with two leading experts:

  • Jackie Bow (Anthropic): Championing the "How to Train Your Dragon" approach, Jackie reveals how we can leverage AI, and even its 'hallucinations,' for advanced threat detection, response, and creative security solutions.
  • Kane Narraway (Canva): Taking the "Knight/Wizard" stance, Kane illuminates the critical challenges in securing AI systems, understanding the new layers of risk, and the complexities of AI threat modeling.


🔥 In this episode, we tackle the tough questions:

  • Is the hype around past 'AI-powered' security justified, or was it "hot garbage"?
  • How can you build effective threat models when AI introduces new, complex failure points?
  • What are the real risks and challenges when implementing AI in production?
  • Can AI tools like 'vibe coding' democratize security, or do they risk deskilling professionals?
  • How can defenders possibly keep pace with AI-driven attacks without fully embracing AI themselves?
  • Exploring the future of AI in both offensive and defensive cybersecurity.


Guest Socials - Jackie's Linkedin + Kane's Linkedin

Podcast Twitter - ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@CloudSecPod⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

If you want to watch videos of this LIVE STREAMED episode and past episodes - Check out our other Cloud Security Social Channels:

-⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Cloud Security Podcast- Youtube⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

- ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Cloud Security Newsletter ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

- ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Cloud Security BootCamp⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

If you are interested in AI Cybersecurity, you can check out our sister podcast -⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ AI Cybersecurity Podcast


Questions asked:

(00:00) Intro: Slaying or Training the AI Dragon at BSidesSF?

(03:15) Meet Jackie Bow (Anthropic): Training AI for Security Defense

(03:41) Meet Kane Narraway (Canva): Securing AI Systems & Facing Risks

(04:51) Was Traditional Security Ops "Hot Garbage"? Setting the Scene

(06:32) The Real Risks: What AI Brings to Your Organisation

(07:27) AI in Action: Leveraging AI for Threat Detection & Response

(08:37) AI Hallucinations: Bug, Feature, or Security Blind Spot?

(09:54) Threat Modeling AI: The Core Challenges & Learnings

(13:29) Getting Started: Practical AI Threat Detection First Steps

(17:56) AI & Cloud: Integrating AI into Your Existing Environments

(25:38) AI vs. Traditional: Is Threat Modeling Different Now?

(29:52) Your First Step: Where to Begin with AI Threat Modeling?

(33:17) Fun Questions & Final Thoughts on the Future of AI Security

Jaksot(345)

 "Escape-Proof" Cloud: How Block built an Automated Approach to Egress Control

"Escape-Proof" Cloud: How Block built an Automated Approach to Egress Control

Many organizations focus on keeping attackers out, but what happens when one gets in? We spoke to Ramesh Ramani, Staff Security Engineer at Block about the real challenge, which is preventing them fro...

1 Heinä 202540min

Prioritizing Cloud Security: How to Decide What to Protect First

Prioritizing Cloud Security: How to Decide What to Protect First

When you can't protect everything at once, how do you decide what matters most? This episode tackles the core challenge of security prioritization. Geet Pradhan, Senior Security Engineer at Lime joins...

23 Kesä 202541min

Migrating from “Tick Box" Compliance to Automating GRC in a Multi-Cloud World

Migrating from “Tick Box" Compliance to Automating GRC in a Multi-Cloud World

In many organizations, security exception management is a manual process, often treated as a simple compliance checkbox. While necessary, this approach can lead to unmonitored configurations that drif...

17 Kesä 202528min

Using AI Agents to Solve Cloud Vulnerability Overload

Using AI Agents to Solve Cloud Vulnerability Overload

In this episode, Ashish Rajan talks with Harry Wetherald, Co-Founder & CEO of Maze, about the reality of modern vulnerability management. They explore why current tools like CNAPPs can generate up to ...

17 Kesä 202538min

Adapting to New Threats, Copilot Risks & The Future of Data (Feat. Matthew Radolec, Varonis)

Adapting to New Threats, Copilot Risks & The Future of Data (Feat. Matthew Radolec, Varonis)

AI is reshaping cybersecurity as we know it. From sophisticated AI-driven phishing attacks to the amplified risk of insider threats using tools like Copilot, the landscape is shifting at an unpreceden...

3 Kesä 202539min

CYBERSECURITY for AI: The New Threat Landscape & How Do We Secure It?

CYBERSECURITY for AI: The New Threat Landscape & How Do We Secure It?

As Artificial Intelligence reshapes our world, understanding the new threat landscape and how to secure AI-driven systems is more crucial than ever. We spoke to Ankur Shah, Co-Founder and CEO of Strai...

20 Touko 202540min

Cloud Security Evolved: From CNAPP to AI Threats

Cloud Security Evolved: From CNAPP to AI Threats

The world of cloud security is evolving at breakneck speed. Are traditional tools and strategies enough to combat the sophisticated threats of tomorrow? In this episode, we're joined by Elad Koren, Vi...

15 Touko 202519min