Power-Softmax is a new HE-compatible attention variant that permits training and inference of billion-parameter polynomial LLMs with performance matching standard transformers.
East: Efficient and accurate secure transformer framework for inference
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
PPHH-VFL splits the model head into a plaintext public part secured by adversarial training and a small MPC private part, yielding up to 6 orders of magnitude faster inference than end-to-end MPC on models up to 86M parameters.
Reduces CKKS homomorphic matrix-vector and matrix-matrix products to plaintext BLAS equivalents, achieving 4-12x overhead versus double-precision floating-point square matrix multiplication.
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
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.
-
Private Vertical Federated Inference for Time-Series
PPHH-VFL splits the model head into a plaintext public part secured by adversarial training and a small MPC private part, yielding up to 6 orders of magnitude faster inference than end-to-end MPC on models up to 86M parameters.
-
Fast Homomorphic Linear Algebra with BLAS
Reduces CKKS homomorphic matrix-vector and matrix-matrix products to plaintext BLAS equivalents, achieving 4-12x overhead versus double-precision floating-point square matrix multiplication.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.