Libsyn Directory

Safe AI Implementation

Release Date: 04/23/2025

Human Side of Fraud: Empathy, Education, & Evolution

Easy Prey

People used to think fraud was something that happened in the shadows, rare, distant, and mostly affecting big companies. But after talking to PJ Rohall, it’s clear that fraud is evolving fast, and it’s showing up in places most of us don’t even think to look. In this episode, I sit down with PJ Rohall, Head of Fraud Strategy and Education at SEON and co-founder of About Fraud. PJ’s work is all about staying ahead of scammers and helping businesses and individuals understand how fraud actually works. From synthetic identities and AI-powered scams to account takeovers and refund fraud,...

Identity Is The New Security Perimeter

Easy Prey

Sometimes it feels like every new technology we adopt comes with a new risk we didn’t see coming. From AI and data breaches to phishing scams and ransomware, it's clear we live in a time when cybersecurity isn’t just a tech issue, it’s a human issue. In this episode, I talk with Jeff Reich, Executive Director of the Identity Defined Security Alliance. Jeff has been in the cybersecurity world since the early days, with decades of experience helping organizations protect what matters most. His passion for identity security and risk management runs deep, and he brings a thoughtful...

Your Car Is Spying On You What It’s Collecting and Who It’s Telling

Easy Prey

I used to think of my car as just a tool to get from point A to point B. But after this conversation, I can’t help but see it as something else entirely, a powerful data collection device that knows far more about me than I realized. From where I go and who I text to how I drive and even what’s on my phone, today’s vehicles are gathering a staggering amount of personal information. In this episode, I talk with Andrea Amico, the founder of . Andrea is one of the leading voices in automotive data privacy and someone who’s spent years uncovering the hidden ways cars collect, store,...

Why Everyone’s A Target

Easy Prey

Some scams are so convincing, they’re almost impossible to spot. With phishing emails that look like they’re from your bank, deep fake videos that mimic real people, and AI-generated messages that feel personal, it’s getting harder to know what’s real and what’s a trap. In this episode, I sit down with Gabrielle Hempel, a security operations specialist at Exabeam and a current law student at Purdue University. Gabrielle brings a sharp perspective shaped by years in cybersecurity, a master’s in cybersecurity and global affairs from NYU, and hands-on experience navigating everything...

Child Exploitation Cyber Investigations

Easy Prey

Technology is a double-edged sword. It can empower us, connect us, and solve problems, but it can also be used to exploit, manipulate, and harm. When it comes to protecting children online, that line gets especially thin. Digital forensics, AI-powered image classification, and global law enforcement collaboration are now essential tools for keeping families safe in a world that moves faster than most of us can keep up. Debbie Garner knows this world intimately. She’s a retired Special Agent in charge with the Georgia Bureau of Investigation and former commander of the state’s Internet...

Reclaiming the Internet

Easy Prey

We may not always understand the evolution of the internet and how tech monopolies exist, but having digital freedom fighters is vital to making conscious change. Today's guest is Cory Doctorow. Cory is a science fiction author, activist, and journalist. He is the author of many books and most recently, Picks and Shovels, The Bezel, and The Lost Cause, a solar punk science fiction novel of hope amidst the climate change emergency. His most recent nonfiction book is the internet con How to Seize the Means of Corruption, a big tech disassembly manual. Other recent books include Red Team...

Security Gaps Hackers Exploit

Easy Prey

Scammers aren’t just phishing your inbox anymore—they’re impersonating your voice, your face, and even your coworkers. Deep fakes and social engineering have moved beyond clever tricks and become powerful tools that bad actors are using to infiltrate businesses, breach accounts, and dismantle trust at scale. What used to take a hacker hours and expensive tools can now be done in minutes by anyone with a Wi-Fi connection and a little malicious intent. Our guest today is Aaron Painter, CEO of Nametag, a company leading the charge in next-generation identity verification. Aaron’s...

Cyber Warfare

Easy Prey

Cyber warfare is no longer something that happens behind closed doors or in some far-off digital corner. It's happening now—and reshaping the rules of conflict in real time. Drone strikes controlled by apps, ransomware attacks on hospitals—today's battleground is just as likely to be online as on the ground. That science fiction scenario is now a critical, constant threat-the kind that affects us all globally. I'm really excited to introduce you to Dr. Chase Cunningham. He's a retired Navy chief cryptologist with a wealth of experience in cyber operations for the NSA, CIA, FBI—and more....

DDoS Attacks

Easy Prey

Scammers are getting smarter, understanding the psychology behind social engineering and the challenges companies face every day can help keep networks secure. This episode will show how to anticipate these threats and secure networks against ever-changing vulnerabilities. We’ll focus on practical, real-world solutions to protect data and trust. Dr. Jared Smith joins us to share his insights from his role leading research and development at SecurityScorecard. He also co-founded UnCat, a B2B accounting technology company serving thousands of customers and teaches as an adjunct professor at...

Safe AI Implementation

Easy Prey

Red models associated with AI technologies highlight real-world vulnerabilities and the importance of proactive security measures. It is vital to educate users about how to explore the challenges and keep AI systems secure. Today’s guest is Dr. Aditya Sood. Dr. Sood is the VP of Security Engineering and AI Strategy at Aryaka and is a security practitioner, researcher, and consultant with more than 16 years of experience. He obtained his PhD in computer science from Michigan State University and has authored several papers for various magazines and journals. In this conversation, he will shed...

More Episodes

Dr. Sood is the VP of Security Engineering and AI Strategy at Aryaka and is a security practitioner, researcher, and consultant with more than 16 years of experience. He obtained his PhD in computer science from Michigan State University and has authored several papers for various magazines and journals.

In this conversation, he will shed light on AI-driven threats, supply chain risks, and practical ways organizations can stay protected in an ever-changing environment. Get ready to learn how the latest innovations and evolving attack surfaces affect everyone from large companies to everyday users, and why a proactive mindset is key to staying ahead.

Show Notes:

[01:02] Dr. Sood has been working in the security industry for the last 17 years. He has a PhD from Michigan State University. Prior to Aryaka, he was a Senior Director of Threat Research and Security Strategy for the Office of the CTO at F5.
[02:57] We discuss how security issues with AI are on the rise because of the recent popularity and increased use of AI.
[04:18] The large amounts of data are convoluting how things are understood, the complexity is rising, and the threat model is changing.
[05:14] We talk about the different AI attacks that are being encountered and how AI can be used to defend against these attacks.
[06:00] Pre-trained models can contain vulnerabilities.
[07:01] AI drift or model or concept drift is when data in the training sets is not updated. The data can be used in a different way. AI hallucinations also can create false output.
[08:46] Dr. Sood explains several types of attacks that malicious actors are using.
[10:07] Prompt injections are also a risk.
[12:13] We learn about the injection mapping strategy.
[13:54] We discuss the possibilities of using AI as a tool to bypass its own guardrails.
[15:18] It's an arms race using AI to attack Ai and using AI to secure AI.
[16:01] We discuss AI workload analysis. This helps to understand the way AI processes. This helps see the authorization boundary and the security controls that need to be enforced.
[17:48] Being aware of the shadow AI running in the background.
[19:38] Challenges around corporations having the right security people in place to understand and fight vulnerabilities.
[20:55] There is risk with the data going to the cloud through the LLM interface.
[21:47] Dr. Sood breaks down the concept of shadow AI.
[23:50] There are also risks for consumers using AI.
[29:39] The concept of Black Box AI models and bias being built into the particular AI.
[33:45] The issue of the ground set of truth and how the models are trained.
[37:09] It's a balancing act when thinking about the ground set of truth for data.
[39:08] Dr. Sood shares an example from when he was researching for his book.
[39:51] Using the push and pretend technique to trick AI into bypassing guardrails.
[42:51] We talk about the dangers of using APIs that aren't secure.
[43:58] The importance of understanding the entire AI ecosystem.

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

Show Notes:

Links and Resources:

TOPICS