What is Azure AI Content Safety?
Azure AI Content Safety is a content moderation platform that uses AI to keep organizational content safe. It is used to create safer online experiences with AI models that detect offensive or inappropriate content in text and images.
Its language models analyze multilingual text, in both short and long form, with an understanding of context and semantics. And it features Vision models that perform image recognition and detect objects in images using "Florence" technology. AI content classifiers identify sexual, violent, hate, and self-harm content with high levels of granularity, and its content moderation severity scores indicate the level of content risk on a scale of low to high.
Its language models analyze multilingual text, in both short and long form, with an understanding of context and semantics. And it features Vision models that perform image recognition and detect objects in images using "Florence" technology. AI content classifiers identify sexual, violent, hate, and self-harm content with high levels of granularity, and its content moderation severity scores indicate the level of content risk on a scale of low to high.
The solution can also be used to establish responsible AI practices by monitoring both user-and AI-generated content. Azure OpenAI Service and GitHub Copilot rely on Azure AI Content Safety to filter content in user requests and responses, ensuring AI models are used responsibly and for their intended purposes.
Categories & Use Cases
Technical Details
| Mobile Application | No |
|---|
FAQs
What is Azure AI Content Safety?
Azure AI Content Safety is a content moderation platform that uses AI to keep organizational content safe. It is used to create safer online experiences with AI models that detect offensive or inappropriate content in text and images.