2 papers
cs.CR2026
Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference
Pranay Anchuri, Matteo Campanelli, Paul Cesaretti +4
When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally…
cs.CR2021
DOVE: A Data-Oblivious Virtual Environment
Hyun Bin Lee, Tushar M. Jois, Christopher W. Fletcher +1
Users can improve the security of remote communications by using Trusted Execution Environments (TEEs) to protect against direct introspection and tampering of sensitive data. This…