Millions of people use cloud-based whiteboard services everyday and as of today, everyone’s privacy from drawings on such whiteboard is under serious threat. Our findings reveal the feasibility of conducting health attribute inference attacks using whiteboard drawings, highlighting the need for privacy enhancements. We pioneer a local differentially private technique tailored to whiteboard that provides rigorous privacy assurances which can be implemented on any whiteboard platform with minimal changes on serverside. Beyond addressing immediate concerns, this approach offers a blueprint for designing specialized privacy mechanisms for emerging collaborative platforms. By equipping users with privacy controls, we can enhance trust of technologies that increasingly mediate human communication and cooperation.

Cloud-based whiteboard services have gained immense popularity, facilitating seamless collaboration and communication. However, the open-ended and persistent nature of whiteboard data exposes privacy vulnerabilities. In this article, we investigate potential health attribute inference attacks that leverage drawings to infer sensitive user information without consent. We develop a local differentially private algorithm that perturbs drawings by spatially deforming them, providing provable privacy guarantees. Our algorithm is implemented in a software tool called DP-WhiteBoard (DP-WB). Extensive experiments demonstrate the algorithm's ability to significantly reduce the accuracy of health attribute inference attacks while maintaining utility for benign recognition tasks. This work represents the first comprehensive study of emerging privacy threats in cloud-based whiteboards, proposing an scalable and adaptable solution with provable privacy guarantee. A demonstration of our work can be found at https://youtu.be/5gD1Te1Fgnw.