According to one embodiment of the present disclosure, an approach is provided in which a processor receives a media stream that includes media content. The processor selects a media stream segment included in the media stream, and generates annotated data based upon a portion of the media content included in the selected media stream segment. The processor, in turn, compares the annotated data with obfuscation preferences that correspond to prohibited content, and modifies the media stream segment in response to the comparison.