AI Threats in 2025: A Year in Review

A 45-minute, data-grounded panel discussion on how AI is reshaping both offense and defense. Topics included the top attack types across Lakera Guard, …

The Call is Coming from Inside the House: When your Agentic Coder Writes Dangerous Code

Introduction

Bianca is a (fictional) developer who wants to use an LLM to help her generate a script to download some of the latest LLM models from …

How We Use Lakera Guard to Secure Our LLMs

Authored technical blog post for Dropbox Tech Blog covering the implementation and deployment of Lakera Guard to protect Dropbox’s LLM-powered …