Behind the Binary by Google Cloud Security
Welcome to Behind the Binary, the podcast that introduces you to the fascinating people, technology, and tools driving the world of reverse engineering. Join your host, Josh Stroschein, a reverse engineer with the FLARE team at Google, and someone passionate about sharing knowledge and shedding light on the art of reverse engineering, as he sits down with intriguing guests to explore the human side of this profession.
Behind the Binary goes beyond the code, sharing the stories, motivations, and unique perspectives of the individuals who dedicate their lives to unraveling the complexities of technology. We'll hear about their journeys into the field, the challenges they face, and the impact their work has on securing our digital world.
Whether you're a seasoned malware analyst, a software developer, a security researcher, or just someone curious about the world of reverse engineering, Behind the Binary offers insightful and engaging conversations for everyone interested in this fascinating field.
Behind the Binary by Google Cloud Security
EP22 Jailbreaking, Prompt Injection, and the "Agentic" Flaw in MCP with Kevin Harris
"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