Hacking AI and Retraining LLMs

Hacking AI and Retraining LLMs

Artificial Intelligence is transforming every industry, but with that transformation comes new security risks. In this episode of The API Hour, host Dan Barahona interviews Robert Herbig, Senior Engineer at SEP and instructor of the APIsec University course, Building Security into AI, to explore the emerging world of AI attacks, data poisoning, and model tampering. From poisoned stop sign datasets to prompt injections that trick LLMs into revealing dangerous information, this episode is packed with eye-opening examples of how AI can be manipulated, and what builders and security teams can do to defend against it. What You’ll Learn * Data poisoning in action: how mislabeled stop signs and manipulated datasets can cause catastrophic AI failures * Watering hole attacks & typosquatting: why malicious datasets and libraries pose a hidden risk * Prompt injection & jailbreaking: real-world cases where LLMs were manipulated into revealing restricted information * Black box vs. white box attacks: what attackers can infer just by observing model confidence scores * Retraining & RAG: how AI models ingest new information and why continuous updates create new vulnerabilities * The API connection: why exposing models via APIs ties AI security directly to API security best practices Episode Timestamps * 00:45 – Stop signs, stripes, and poisoned training data * 07:00 – Data poisoning in Gmail spam detection * 17:00 – SEO hacks and AI summaries: a new frontier for attackers * 22:00 – Typo-squatting and malicious packages * 25:00 – Pliny the Liberator and “memetic viruses” in training data * 33:00 – Black box vs. white box attacks on computer vision models * 43:00 – Prompt injection and roleplay exploits * 52:00 – APIs and AI security: two sides of the same coin

Inside this Year's Biggest API breaches: Real Stories, Real Lessons

In this episode of The Appi Hour, Dan is joined by Dave, Head of Products at APIsec, to unpack some of the most eye-opening API breaches making waves. From leaked API keys at xAI, to McDonald’s exposing 64 million job applications, to logic flaws in Base44’s vibe-coding platform, and even a Volkswagen app that let attackers brute-force their way into cars—the stories are as shocking as they are instructive. Dave brings frontline experience from working with customers on API security, highlighting how seemingly small oversights—like hardcoded keys, weak authentication, or unchecked authorization—can snowball into massive vulnerabilities. Together, they connect each case to the OWASP API Security Top 10 and share practical steps to avoid these same pitfalls. Whether you’re a developer, security engineer, or simply curious about how everyday apps get hacked, this conversation offers valuable insights (and a reminder of how critical APIs are in today’s digital world). What you’ll learn: * Why API keys remain one of the most common—and preventable—security leaks * How researchers accessed 64 million McDonald’s job applications via a simple IDOR flaw * The hidden risks of convenience-driven platforms like Base44 * How a used Volkswagen exposed its owner’s data through predictable APIs * Best practices for preventing brute force, excessive data exposure, and broken authorization Tune in, take notes, and walk away with actionable tactics to strengthen your own API security posture.

Breaking your Build Before Hackers Do

API Security Meets DevSecOps with Scott Bly In this episode of The API Hour, cybersecurity expert Scott Bly joins host Dan Barahona to explore how integrating security into the DevOps lifecycle, aka DevSecOps, transforms API protection. From threat modeling and security metrics to the role of AI and gamification, this is a must-listen for teams aiming to balance speed with security. Learn how to embed security culture across development teams and build smarter, safer APIs.