2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
HE-OFT is presented, the first cryptographically secure one-shot federated fine-tuning protocol in which no party receives the trained model.
Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the computation without revealing the prompt. Existing secure inference systems run a forward pass without consuming a token under encryption, and generating text with them requi...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
