AI security is no longer just about blocking malicious prompts. As Agentic AI systems gain the ability to autonomously access data, move files, and make decisions, organizations face new risks that extend across the entire AI ecosystem—from models and training data to open-source dependencies and user interactions. Compromised or poisoned LLMs can lead to data leaks, unauthorized access, and even the creation of malicious code, making AI environments an increasingly attractive target for cybercriminals.

Kaspersky expert will share the latest threat intelligence on AI-driven attacks, real-world case studies, and practical strategies for securing Agentic AI and LLM deployments. Learn how Kaspersky helps organizations detect emerging threats, identify malicious models and dependencies, and protect AI systems throughout their lifecycle.