Sometimes we forget how much trust we place in the little things around us like a lock on a door or a badge on someone's shirt. We see those symbols and assume everything behind them is safe, but it doesn't always work that way. A person with enough confidence, or the right story, can slip through places we think are locked down tight, and most of us never notice it's happening.

My guest today is Deviant Ollam, and he's one of the rare people who gets invited to break into buildings on purpose. He talks about how he fell into this unusual line of work, the odd moments that shaped his career, and why understanding human behavior matters just as much as understanding locks or alarms. Listening to him describe these situations, where he's walking through offices, popping doors, or blending in with repair crews, makes you realize how blind we can be to our own surroundings.

We also get into the practical side of things: the mistakes companies make, the small fixes that go a long way, and why teaching employees to slow down and ask a few extra questions can make all the difference. It's an eye-opening conversation, especially if you've ever assumed your workplace is more secure than it really is.

• [03:24] Deviant shares how early adventures, abandoned buildings, and curiosity about locks pulled him toward physical security.
• [06:20] A story about a law firm reveals how an office "secure" door was bypassed instantly, exposing major hardware flaws.
• [09:16] Discussion shifts to how the locksmith and safe technician community reacted to his public teaching and how that's changed over time.
• [13:28] The topic turns to security theater and the gap between feeling safe and actually being protected.
• [16:18] An explanation of symbolic locks versus real security products highlights how easily people mix up the two.
• [19:11] Conversation moves into the lack of clear U.S. lock standards and why European systems make things easier for consumers.
• [21:51] Layered security comes into focus, emphasizing that the goal is to delay and deter rather than stop every possible attack.
• [24:35] Monitoring tools, overlooked windows, and forgotten blind spots show how attackers often choose the easiest entry point.
• [27:38] We look at the politics of penetration tests and why coordinating with building management is essential.
• [31:28] Escalation testing illustrates how long suspicious behavior can go unnoticed inside an organization.
• [34:34] The need for simple, obvious reporting channels becomes clear when employees aren't sure who to alert.
• [37:00] A breakdown of common cover stories shows why attackers lean on confidence and industry jargon.
• [39:50] Urgency and pressure tactics surface as key components of social engineering and why "polite paranoia" helps.
• [41:14] A viral prank underscores how easily an unverified person can be escorted into restricted areas.

Thanks for joining us on Easy Prey. Be sure to subscribe to our podcast on iTunes and leave a nice review.

• Podcast Web Page
• Facebook Page
• whatismyipaddress.com
• Easy Prey on Instagram
• Easy Prey on Twitter
• Easy Prey on LinkedIn
• Easy Prey on YouTube
• Easy Prey on Pinterest
• Deviant Ollam
• Deviant Ollam - You Tube
• Deviant Ollam - Instagram
• Practical Lock Picking: A Physical Penetration Tester's Training Guide

AI has brought incredible new capabilities into everyday technology, but it's also creating security challenges that most people haven't fully wrapped their heads around yet. As these systems become more capable and more deeply connected to the tools and data we rely on, the risks become harder to predict and much more complicated to manage.

My guest today is Rich Smith, who leads offensive research at MindGard and has spent more than twenty years working on the front lines of cybersecurity. Rich has held leadership roles at organizations like Crash Override, Gemini, Duo Security, Cisco, and Etsy, and he's spent most of his career trying to understand how real attackers think and where systems break under pressure.

We talk about how AI is changing the way attacks happen, why the old methods of testing security don't translate well anymore, and what happens when models behave in ways no one expected. Rich also explains why psychology now plays a surprising role in hacking AI systems, where companies are accidentally creating new openings for exploitation, and what everyday users should keep in mind when trusting AI with personal information. It's a fascinating look behind the curtain at what's really going on in AI security right now.

• [01:00] Rich describes getting into hacking as a kid and bypassing his brother's disk password.
• [03:38] He talks about discovering Linux and teaching himself through early online systems.
• [05:07] Rich explains how offensive security became his career and passion.
• [08:00] Discussion of curiosity, challenge, and the appeal of breaking systems others built.
• [09:45] Rich shares surprising real-world vulnerabilities found in large organizations.
• [11:20] Story about discovering a major security flaw in a banking platform.
• [12:50] Example of a bot attack against an online game that used his own open-source tool.
• [16:26] Common security gaps caused by debugging code and staging environments.
• [17:43] Rich explains how AI has fundamentally changed offensive cybersecurity.
• [19:30] Why binary vulnerability testing no longer applies to generative AI.
• [21:00] The role of statistics and repeated prompts in evaluating AI risk and failure.
• [23:45] Base64 encoding used to bypass filters and trick models.
• [27:07] Differentiating between model safety and full system security.
• [30:41] Risks created when AI models are connected to external tools and infrastructure.
• [32:55] The difficulty of securing Python execution environments used by AI systems.
• [35:56] How social engineering and psychology are becoming new attack surfaces.
• [38:00] Building psychological profiles of models to manipulate behavior.
• [42:14] Ethical considerations and moral questions around AI exploitation.
• [44:05] Rich discusses consumer fears and hype around AI's future.
• [45:54] Advice on privacy and cautious adoption of emerging technology.

Thanks for joining us on Easy Prey. Be sure to subscribe to our podcast on iTunes and leave a nice review.

• Podcast Web Page
• Facebook Page
• whatismyipaddress.com
• Easy Prey on Instagram
• Easy Prey on Twitter
• Easy Prey on LinkedIn
• Easy Prey on YouTube
• Easy Prey on Pinterest
• Mindgard
• Rich.Smith@Mindgard.ai