Скачать или смотреть Secure AI Starts Here: Best Practices for Securing AI Development

As AI becomes deeply embedded into critical systems, securing your AI models and infrastructure isn't just a nice-to-have—it’s mission-critical. In this webinar, TrojAI and JFrog dive into the evolving threats across the AI software supply chain, from model poisoning and prompt injection to compromised open-source dependencies and unsafe serialization formats.

We unpack how enterprises can identify and mitigate these risks using capabilities like AI discovery, AI model scanning, red teaming, and runtime defenses. Whether you're building with open-source models, managing enterprise LLM usage, or deploying AI into production, this session gives you the strategies and tools needed to stay one step ahead of the threat landscape.

Key Takeaways:
What the AI supply chain really is and where its hidden risks lie
How attackers are exploiting model vulnerabilities, ranging from insecure model formats to model behavior
Practical steps to secure your AI development practices