Visual assistance technologies provide people who are blind with access to information about their visual surroundings by digitally connecting them to remote humans or artificial intelligence systems that describe visual content such as objects, people, scenes, and text observed in their live image/video feeds. Prior work has revealed that users have concerns about how such technologies handle private visual content captured in their image/video feeds. Yet, it remains unclear how users want technologies to manage such private content. To fill this gap, we interviewed 16 totally blind individuals to learn about their expectations for visual privacy when using visual assistance technologies. Our findings reveal three overarching user-centered expectations associated with visual privacy-preservation in this domain, as well as the broader ethical challenges involved with developing AI-based privacy-preserving visual assistance technologies.