arXiv cs.CR·2d agoTrusted Model Environment for Private Semantic Computations#tee#trusted-execution-environment#privacyResearch
arXiv cs.CR·11d agoROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation#ckks#cryptography#homomorphic-encryptionResearch1
arXiv cs.CR·11d agoOptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design#dnn#hardware-acceleration#homomorphic-encryptionResearch