Power-Softmax is a new HE-compatible attention variant that permits training and inference of billion-parameter polynomial LLMs with performance matching standard transformers.
Homomorphic encryption for arithmetic of approximate numbers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
CPPDD is a new consensus-based protocol for privacy-preserving multi-client data sharing that achieves unanimous-release confidentiality, linear scalability, and high-probability malicious deviation detection.
citing papers explorer
-
Power-Softmax: Towards Secure LLM Inference over Encrypted Data
Power-Softmax is a new HE-compatible attention variant that permits training and inference of billion-parameter polynomial LLMs with performance matching standard transformers.
-
Secure, Verifiable, and Scalable Multi-Client Data Sharing via Consensus-Based Privacy-Preserving Data Distribution
CPPDD is a new consensus-based protocol for privacy-preserving multi-client data sharing that achieves unanimous-release confidentiality, linear scalability, and high-probability malicious deviation detection.