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

Criminals are always adapting. Whether it's copper wiring stripped from job sites or porch pirates grabbing deliveries in broad daylight, they keep finding new ways to take what isn't theirs. But maybe prevention isn't about harsher punishment or more cameras. Maybe it's about smarter design and understanding what drives people to steal in the first place.

My guest today is Dr. Ben Stickle, a professor of criminal justice at Middle Tennessee State University and one of the country's top researchers on property crime. Before entering academia, he worked in law enforcement, which gives him a rare mix of real-world perspective and research-based insight. His work on metal theft, catalytic converter crime, and package theft sheds light on who's actually committing these offenses, what motivates them, and which prevention methods truly work.

We discuss how fluctuating metal prices influence theft rates, why cameras often fail to stop certain crimes, and how a few simple design changes to your home can make a real difference. Dr. Stickle also shares unexpected examples of modern theft, from stolen pets to disappearing beehives, and explains how communities can act early before small trends turn into national headlines.

• [01:22] Ben recalls his early years as a police officer and what motivated him to serve.
• [01:27] The conversation moves into crime scene investigation training and lessons from real-world cases.
• [03:38] Ben talks about transitioning into teaching and research, guided by a drive to improve policing through knowledge.
• [05:30] The focus turns to crime prevention and understanding how to stop crimes before they happen.
• [06:15] Discussion shifts to metal theft, from copper wiring to catalytic converters, and the steep cost of replacing what's stolen.
• [10:47] Ben explains how metal theft isn't new, tracing its roots all the way back to ancient Greece.
• [14:58] The challenges of balancing better security design with cost and practicality come to light.
• [17:46] The topic turns to porch piracy and why package theft has become one of the most common crimes in America.
• [19:43] Ben breaks down how daily routines influence theft risk and how thieves range from organized groups to impulsive opportunists.
• [25:23] The role of cameras is questioned as Ben explains why surveillance doesn't always deter crime.
• [27:00] Practical prevention strategies emerge like delivering to lockers, hiding packages, and using better drop-off options.
• [28:53] New tech enters the discussion with alarms, GPS tracking, and geofencing tools designed to stop porch pirates.
• [29:14] Ben explores how rethinking porch layouts could help protect deliveries and reduce crime opportunities.
• [31:47] The conversation expands to environmental criminology and how physical spaces can influence criminal behavior.
• [34:00] Ben emphasizes the importance of targeted prevention instead of one-size-fits-all solutions.
• [38:00] The value of using local crime data, rather than fear-driven news, to make safety decisions is underscored.
• [40:30] Emerging trends come up, from pet and beehive thefts to crimes tied to the growing sharing economy.
• [42:00] The episode wraps with takeaways on prevention, awareness, and where listeners can find Ben's research.

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
• The Knoble
• Freddy Massimi - LinkedIn