Safer and Multimodal: Responsible AI with Gemma- Google Developers Blog

What this post added

Introduces ShieldGemma 2, a 4B parameter safety classifier model built on Gemma 3, extending safety capabilities to image analysis for multimodal AI. It can be used as an input filter for vision language models or an output filter for image generation systems, handling both synthetic and natural images. The model is trained on curated datasets and instruction-tuned for performance, with a focus on detecting sexually explicit, dangerous, and violent content. It offers flexibility for fine-tuning, versatility across Gemma 3 supporting frameworks, and an open, collaborative approach.