Massachusetts Institute of Technology researchers developed a protocol that safeguards personal data while ensuring algorithmic-based product recommendations are accurate. The protocol also minimizes the unauthorized transfer of information from a database in the event a malicious actor tries to trick the server into leaking data. “A malicious client won’t learn much more information than an honest client following protocol. And it protects against malicious servers, too,” Computer Science and Artificial Intelligence Laboratory graduate student Simon Langowski said.