Easy Prey26 Nov 2025

Hacking AI

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.

Show Notes:

[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.

Links and Resources:

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(329)

Job Recruiter Scams

Job hunting is hard enough without having to stop and ask whether the recruiter in your inbox is even real. My guest today, Jay Jones, ran into that problem firsthand after being laid off in December ...

24 Juni 35min

Bail Bonds Scams

Getting a call that someone you love has been arrested is scary enough. Getting that call from someone who sounds official, knows just enough to seem credible, and says you have to send money right aw...

17 Juni 36min

Confessions of a Fraudster

Technology keeps changing, but many of the most effective scams still come down to something very human: trust. My guest today is Tony Sales, co-founder of We Fight Fincrime and Underworld TV. Tony ha...

10 Juni 54min

Personal Safety

Scams and safety threats don't always announce themselves. Sometimes they start quietly, with a moment of distraction, a strange feeling you ignore, or a situation that shifts just enough to test whet...

3 Juni 43min

Data For Sale

Everyday conveniences ask for tiny pieces of information all the time like a phone number at checkout, a zip code at the register, an email address for a receipt, or a loyalty account for a small disc...

27 Maj 43min

Exploiting Psychology

Scams are often explained as a failure of judgment, but the truth is far more human. People are not fooled because they are foolish. They are manipulated at the exact moment emotion overrides logic, w...

20 Maj 45min

Investment Traps

Investment losses can be confusing because they do not always tell the whole story. Sometimes money is lost because the market has changed. Other times, an investor was sold something they did not und...

13 Maj 47min

Elder Exploitation

Aging parents often rely on the people closest to them for help, but what happens when that help becomes a way to take control? For Charles Wallace, the warning signs started small. His mother's fridg...

6 Maj 39min