EP230 AI Red Teaming: Surprises, Strategies, and Lessons from Google
Cloud Security Podcast by Google
Release Date: 06/16/2025
Cloud Security Podcast by Google
Guest: , Founder and CEO, Citreno Topics: Why do so many organizations still collect logs yet don’t detect threats? In other words, why is our industry spending more money than ever on SIEM tooling and still not “winning” against Tier 1 ... or even Tier 5 adversaries? What are the hardest parts about getting the right context into a SOC analyst’s face when they’re triaging and investigating an alert? Is it integration? SOAR playbook development? Data enrichment? All of the above? What are the organizational problems that keep organizations from getting the full benefit...
info_outlineCloud Security Podcast by Google
Guest: , Product Security Engineering Manager, Google Cloud Topic: Could you share insights into how Product Security Engineering approaches at Google have evolved, particularly in response to emerging threats (like Log4j in 2021)? You mentioned applying SRE best practices in detection and response, and overall in securing the Google Cloud products. How does Google balance high reliability and operational excellence with the needs of detection and response (D&R)? How does Google decide which data sources and tools are most critical for effective D&R? How do we deal with high...
info_outlineCloud Security Podcast by Google
Guest: , Privacy Engineer, Google Topic: You have had a fascinating career since we [Tim] graduated from college together – you mentioned before we met that you’ve consulted with a literal world leader on his personal digital security footprint. Maybe tell us how you got into this field of helping organizations treat sensitive information securely and how that led to helping keep targeted individuals secure? You also work as a privacy engineer on , Google’s new operating system kernel. How did you go from human rights and privacy to that? What are the key privacy...
info_outlineCloud Security Podcast by Google
Guest: , Staff Adoption Engineer, Google Cloud Topic: Detection as code is one of those meme phrases I hear a lot, but I’m not sure everyone means the same thing when they say it. Could you tell us what you mean by it, and what upside it has for organizations in your model of it? What gets better for security teams and security outcomes when you start managing in a DAC world? What is primary, actual code or using SWE-style process for detection work? Not every SIEM has a good set of APIs for this, right? What’s a team to do in a world of no or low API support for this model? If...
info_outlineCloud Security Podcast by Google
Guest: , Principal Digital Arsonist, Google Topic: Your RSA talk highlights lessons learned from two years of AI red teaming at Google. Could you share one or two of the most surprising or counterintuitive findings you encountered during this process? What are some of the key differences or unique challenges you've observed when testing AI-powered applications compared to traditional software systems? Can you provide an example of a specific TTP that has proven effective against AI systems and discuss the implications for security teams looking to detect it? What practical advice would you...
info_outlineCloud Security Podcast by Google
Guest: , Associate Director of Threat Intelligence, Verizon Business, Lead the Verizon Data Breach Report Topics: How would you define “a cloud breach”? Is that a real (and different) thing? Are cloud breaches just a result of leaked keys and creds? If customers are responsible for 99% of cloud security problems, is cloud breach really about ? Are misconfigurations really responsible for so many cloud security breaches? How are we at configuration? What parts of DBIR are not total ? Something about vuln exploitation vs credential abuse in today’s breaches–what’s...
info_outlineCloud Security Podcast by Google
Guest , Co-founder and CTO @ Topics: SIEM is hard, and many vendors have discovered this over the years. You need to get storage, security and integration complexity just right. You also need to be better than incumbents. How would you approach this now? vs SIEM/EDR/XDR combo. These point in the opposite directions, which side do you think will win? In a world where data volumes are exploding, especially in cloud environments, you're building a SIEM with ClickHouse as its backend, focusing on both parsed and raw logs. What's the core advantage of this approach, and how does it address the...
info_outlineCloud Security Podcast by Google
Guests: , CEO of , CTO of Tenex.AI Topics: Why is your AI-powered MDR special? Why start an MDR from scratch using AI? So why should users bet on an “AI-native” MDR instead of an MDR that has already got its act together and is now applying AI to an existing set of practices? What’s the current breakdown in labor between your human SOC analysts vs your AI SOC agents? How do you expect this to evolve and how will that change your unit economics? What tasks are humans uniquely good at today’s SOC? How do you expect that to change in the next 5 years? We hear...
info_outlineCloud Security Podcast by Google
Guest: , Cloud Security Architect, Google Cloud Topics: Can you describe the key components of an AI software supply chain, and how do they compare to those in a traditional software supply chain? I hope folks listening have heard past episodes where we talked about poisoning training data. What are the other interesting and unexpected security challenges and threats associated with the AI software supply chain? We like to say that history might not repeat itself but it does rhyme – what are the rhyming patterns in security practices people need to be aware of when it...
info_outlineCloud Security Podcast by Google
Hosts: , Customer Advocacy Lead, Office of the CISO, Google Cloud , Director, Office of the CISO, Google Cloud Guest: , Strategic Advisor and Investor Resources: (as aired originally) podcast site
info_outlineGuest:
- Daniel Fabian, Principal Digital Arsonist, Google
Topic:
- Your RSA talk highlights lessons learned from two years of AI red teaming at Google. Could you share one or two of the most surprising or counterintuitive findings you encountered during this process?
- What are some of the key differences or unique challenges you've observed when testing AI-powered applications compared to traditional software systems?
- Can you provide an example of a specific TTP that has proven effective against AI systems and discuss the implications for security teams looking to detect it?
- What practical advice would you give to organizations that are starting to incorporate AI red teaming into their security development lifecycle?
- What are some initial steps or resources you would recommend they explore to deepen their understanding of this evolving field?
Resources:
- Video (LinkedIn, YouTube)
- Google's AI Red Team: the ethical hackers making AI safer
- EP217 Red Teaming AI: Uncovering Surprises, Facing New Threats, and the Same Old Mistakes?
- EP150 Taming the AI Beast: Threat Modeling for Modern AI Systems with Gary McGraw
- EP198 GenAI Security: Unseen Attack Surfaces & AI Pentesting Lessons
- Lessons from AI Red Teaming – And How to Apply Them Proactively [RSA 2025]