You have an Azure subscription. You are building a social media app that will enable users to share images. You need to ensure that inappropriate…

The goal is to block inappropriate image content in a social media app with minimal development effort. Both Azure AI Vision and Azure AI Content Safety provide pre-trained models accessible via simple API calls, directly addressing this need.

Azure AI Vision includes an Image Analysis feature that can detect adult, racy, and gory content. This is a ready-to-use capability that requires no model training.

Azure AI Content Safety is a dedicated service designed specifically for content moderation. It detects a range of inappropriate content in images and text, including hate, sexual, violence, and self-harm, making it an ideal solution for this scenario.

Using these pre-built services significantly reduces development time compared to building a custom solution.

A. Microsoft Defender for Cloud Apps: This is a Cloud Access Security Broker (CASB) for monitoring and protecting data in sanctioned cloud apps, not for content moderation within a custom-built application.

B. Azure AI Custom Vision: This service is used to build and train custom image classification models. This would require significant development effort to gather data, label it, and train a model, violating a key requirement.

E. Azure AI Document Intelligence: This service is designed to extract text and structure from documents and forms. It is not intended for moderating general image content for appropriateness.

1. Azure AI Content Safety: Microsoft Learn. "What is Azure AI Content Safety?". This document states, "Azure AI Content Safety is a content moderation service that helps you detect harmful user-generated and AI-generated content... It can detect harmful material in both text and images." This directly supports its use for the described scenario.

2. Azure AI Vision: Microsoft Learn. "Detect adult content - Image Analysis 4.0". The documentation for the Image Analysis service states, "Image Analysis can detect adult material in images so that developers can restrict the display of these images in their software. Content flags are applied with a score between zero and one so developers can interpret the results according to their own preferences." This confirms its capability for content moderation with minimal effort.

3. Azure AI Custom Vision: Microsoft Learn. "What is Custom Vision?". The documentation states, "Custom Vision is an image recognition service that lets you build, deploy, and improve your own image identifiers." This confirms it is for building custom models, which is more effort than using a pre-built service.