ABOUT THIS EPISODE
"Skilled adversaries have a 100% success rate against all of the defenses that we know about."
In this episode, Kevin Harris defends that claim. We move past the standard "AI Safety" talking points to distinguish between the two attack vectors confusing the industry: Prompt Injection (an application-layer failure) vs. Jailbreaking ("gaslighting" the model via context shifting).
Kevin argues that we haven't actually invented AI yet—we've just built a mirror that reflects our own intelligence (and psychosis) back at us. We also dissect the new model context protocol (MCP) and why giving "discretion" to agents that cannot think is potentially repeating the security mistakes of Web 2.0.
THE SESSION:
- The "Pirate" Jailbreak: Why telling a model to be a pirate isn't just a party trick—it's a method of shifting the context window to bypass refusal patterns.
- The 100% Failure Rate: Why current defenses are only speed bumps for skilled adversaries, and why you are attacking the application, not the model.
- "There Is No AI": Kevin’s theory on why LLMs are just "predictive text made 3 orders of magnitude better" and the danger of "AI-induced psychosis".
- The Agentic Threat (MCP): A deep dive into the model context protocol. Why client-side authorization is the new "Browser Security" battleground, and why we are handing "table saws" to users who don't know how to use them.
- The Fix: Why "Attention Functions" are the key to understanding (and securing) the future of these models.
Join the Community
- Research Hub: Threat research, training events and news:
https://cloud.google.com/security/flare - The FLARE Insider: Get community updates and announcements. To subscribe, email flare-external@google.com
FOLLOW THE SHOW:
- Subscribe: Apple Podcasts | Spotify | YouTube
English
United States
TRANSCRIPT 🔗
Are you the producer of this podcast?
Add a podcast transcript
Need Audio-to-Text?
Transcribe with Listen411 in Just 60 Seconds
SEARCH PAST EPISODES
Search past episodes of Behind the Binary by Google Cloud Security.
OTHER EPISODES IN THIS PODCAST
In this episode, Dhillon Kannabhiran shares the gritty origin story of Hack in the Box (HITB), detailing how he dug a $20k financial hole to launch the first event in Malaysia before building it into a global brand.
The conversation moves beyond conferences to explore the cutting edge of technology…
In this episode, we’re joined by Nino Isakovic, a long-time low-level security expert, for a thought-provoking conversation that spans the foundational and the cutting-edge. Nino discusses the art of deconstructing problems—sharing insights on how to learn effectively, the building blocks of a robu…
In this episode, we get a unique look at the history of Windows through the eyes of one of its leading experts, Pavel Yosifovich. We delve into his fascinating origin story, including the "fluke" that led him to become the author of the legendary Windows Internals series, and why he descr…
In this episode, we sit down with Nick Harbour, Blas Kojusner, Moritz Raabe, and Sam Kim — members of the FLARE Team and some of this year’s challenge authors — for a deep dive into the design and execution of FLARE-On 12. The team discusses the complexity and intent behind this year's challen…
Disclaimer: The podcast and artwork embedded on this page are from Josh Stroschein, which is the property of its owner and not affiliated with or endorsed by Listen Notes, Inc.
EDIT
Thank you for helping to keep the podcast database up to date.
