March 18, 2024, 4:47 a.m. | Roy Weiss, Daniel Ayzenshteyn, Guy Amit, Yisroel Mirsky

cs.CL updates on arXiv.org arxiv.org

arXiv:2403.09751v1 Announce Type: cross
Abstract: AI assistants are becoming an integral part of society, used for asking advice or help in personal and confidential issues. In this paper, we unveil a novel side-channel that can be used to read encrypted responses from AI Assistants over the web: the token-length side-channel. We found that many vendors, including OpenAI and Microsoft, have this side-channel.
However, inferring the content of a response from a token-length sequence alone proves challenging. This is because tokens …

abstract advice ai assistants arxiv assistants cs.ai cs.cl cs.cr integral novel paper part prompt responses society token type web

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote