Mitigating a token-length side-channel attack in our AI products
Since the discovery of CRIME, BREACH, TIME, LUCKY-13 etc., length-based side-channel attacks have been considered practical. Even though packets were encrypted, attackers were able to infer information about the underlying plaintext by analyzing metadata like the packet length or timing information. Cloudflare was recently contacted by a group of researchers at Ben Gurion University who wrote a paper titled “What Was Your Prompt?