AEGIS reduces inter-GPU communication by up to 81.3% in self-attention and reaches 96.62% scaling efficiency with 3.86x speedup on four GPUs for 2048-token encrypted Transformer inference.
Tenseal: A library for en- crypted tensor operations using homomorphic en- cryption
4 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
4
Pith papers citing it
20
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
pFedCKKS derives CKKS parameter constraints for PFL under 128-bit security reducing choices to inner and outer ciphertext primes and evaluates precision-cost trade-offs on FEMNIST, CelebA and Sentiment140.
FedShield-LLM integrates pruning and FHE on LoRA parameters to support secure, scalable federated fine-tuning of LLMs such as Llama-2.
FL with homomorphic encryption matches centralized ML performance for CVD risk prediction but adds cryptographic overhead, while DP-FL has lower cost yet greater accuracy loss especially for logistic regression.
citing papers explorer
-
AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems
AEGIS reduces inter-GPU communication by up to 81.3% in self-attention and reaches 96.62% scaling efficiency with 3.86x speedup on four GPUs for 2048-token encrypted Transformer inference.
-
Exploring CKKS Parameter Trade-offs for Privacy-Preserving Personalized Federated Learning
pFedCKKS derives CKKS parameter constraints for PFL under 128-bit security reducing choices to inner and outer ciphertext primes and evaluates precision-cost trade-offs on FEMNIST, CelebA and Sentiment140.
-
FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model
FedShield-LLM integrates pruning and FHE on LoRA parameters to support secure, scalable federated fine-tuning of LLMs such as Llama-2.
-
Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling
FL with homomorphic encryption matches centralized ML performance for CVD risk prediction but adds cryptographic overhead, while DP-FL has lower cost yet greater accuracy loss especially for logistic regression.