AutoPoly-HE: Autonomous Design of Polynomial Activations for Privacy-Preserving Encrypted Inference
AutoPoly-HE automatically designs polynomial activations for encrypted inference across ResNet and Vision Transformer models.
Stories per day · 30 days
2 RSS
Relatedautoply-he1encrypted-inference1homomorphic-encryption1polynomial-activation1resnet1vision-transformer1
3 stories, newest first · one card per story
Stories tagged #privacy-preserving-ml
Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints
A new operator stabilizes deep reinforcement learning when training runs under fully homomorphic encryption constraints.
HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
HE-Guardrail detects LLM jailbreaks during encrypted inference without decrypting client prompts.