Lakera Launches Open-Source Security Benchmark for LLM Backends in AI Agents

Core Insights - Check Point Software Technologies Ltd. and Lakera have announced the release of the backbone breaker benchmark (b3), an open-source security evaluation specifically designed for assessing the security of large language models (LLMs) within AI agents [1] Company Overview - Check Point Software Technologies Ltd. is recognized as a pioneer and global leader in cyber security solutions [1] - Lakera is identified as a world-leading AI-native security platform focused on Agentic AI applications [1] Industry Context - The collaboration between Check Point and Lakera, along with researchers from The UK AI Security Institute, highlights the growing importance of security evaluations in the rapidly evolving field of AI [1] - The b3 benchmark aims to address security concerns related to LLMs, which are increasingly integrated into various AI applications [1]