# Protecting AI Systems: Understanding Vulnerabilities and Attack Surfaces

Page: https://stenobird.com/podcast/ai-engineering-podcast/protecting-ai-systems-understanding-vulnerabilities-and-attack-surfaces
Text version: https://stenobird.com/podcast/ai-engineering-podcast/protecting-ai-systems-understanding-vulnerabilities-and-attack-surfaces.md
Podcast: [AI Engineering Podcast](https://stenobird.com/podcast/ai-engineering-podcast)
Published: 2025-05-03T22:32:44+00:00
Episode link: https://www.aiengineeringpodcast.com/hiddenlayer-shadow-logic-shadow-genes-ai-security-episode-50
Audio file: https://op3.dev/e/dts.podtrac.com/redirect.mp3/serve.podhome.fm/episode/f6ff0caa-931b-4c08-bfdd-08dc7f5cd336/638818928977984630012350a4-d95b-4694-aeb8-f267bc35ff38v1.mp3
Processing state: failed
JSON: https://stenobird.com/v1/public/podcasts/ai-engineering-podcast/episodes/protecting-ai-systems-understanding-vulnerabilities-and-attack-surfaces
Duration seconds: 3109

## Resource

Summary In this episode of the AI Engineering Podcast Kasimir Schulz, Director of Security Research at HiddenLayer, talks about the complexities and security challenges in AI and machine learning models. Kasimir explains the concept of shadow genes and shadow logic, which involve identifying common subgraphs within neural networks to understand model ancestry and potential vulnerabilities, and emphasizes the importance of understanding the attack surface in AI integrations, scanning models for security threats, and evolving awareness in AI security practices to mitigate risks in deploying AI systems. Announcements Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems Your host is Tobias Macey and today I'm interviewing Kasimir Schulz about the relationships between the various models on the market and how that information helps with selecting and protecting models for your applications Interview Introduction How did you get involved in machine learning? Can you start by outlining the current state of the threat landscape for ML and AI systems? What are the main areas of overlap in risk profiles between prediction/classification and generative models? (primarily from an attack surface/methodology perspective) What are the significant points of divergence? What are some of the categories of potential damages that can be created through the deployment of compromised models? How does the landscape of foundation models introduce new challenges around supply chain security for organizations building with AI? You recently published your findings on the potential to inject subgraphs into model architectures that are invisible during normal operation of the model. Along with that you wrote about the…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/ai-engineering-podcast/episodes/protecting-ai-systems-understanding-vulnerabilities-and-attack-surfaces/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/ai-engineering-podcast/protecting-ai-systems-understanding-vulnerabilities-and-attack-surfaces.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.