Sandboxing Agents: Principles and Mistakes

Send us a text

Researchers Yifeng (Ethan) He and Peter Rong join host Madi Vorbrich to break down their paper "Security of AI Agents." They explore real-world AI agent threats, like session hijacks and tool-based jailbreaks, and share practical defenses, from sandboxing to agent-to-agent protocols.

Full transcript with links to resources available at https://mlsecops.com/podcast/ai-agent-security-threats-defenses-for-modern-deployments

Thanks for checking out the MLSecOps Podcast! Get involved with the MLSecOps Community and find more resources at https://community.mlsecops.com.

Additional tools and resources to check out:
Protect AI Guardian: Zero Trust for ML Models

Recon: Automated Red Teaming for GenAI

Protect AI’s ML Security-Focused Open Source Tools

LLM Guard Open Source Security Toolkit for LLM Interactions

Huntr - The World's First AI/Machine Learning Bug Bounty Platform