Pacifo speeds encrypted ResNet20 inference while keeping most accuracy
Runtime is 3.7 to 21.7 times faster than prior FHE ResNet20 work, retaining 95% to 99% plaintext accuracy.
Stories per day · 30 days
Relatedfully-homomorphic-encryption2ckks1cryptography1gelu1llm1mlaas1pacifo1privacy1resnet1silu1systematization1transformers1
6 stories, newest first · one card per story
Stories tagged #private-inference
SPA approximates gated activations for faster FHE inference
On [-5,5], SPA-balanced is 3.25× faster than MOAI for erf-GELU at comparable error.
A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference
A cs.CR study graphs 62 private Transformer inference systems and finds almost none are directly comparable.
Trusted Model Environment for Private Semantic Computations
Researchers propose trusted model environments that run generative models inside TEEs for private semantic computation.
ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation
ROSETTA is a hybrid CKKS/TFHE homomorphic encryption framework for privacy-preserving LLM decoding, achieving up to 4.8x Softmax and 2.1x end-to-end speedups.
OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design
OptiPrime co-designs HE-MPC protocols with hardware acceleration to remove network communication bottlenecks in private DNN inference, beating Cheetah by up to 5.7x.