Introduces formal verification to compute certified neuron range bounds for CKKS-encrypted neural networks, eliminating overflow failures that previously reached 47%.
Orion: A fully homomorphic encryption framework for deep learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
A full-system energy model shows NISQ quantum simulations dominated by error mitigation sampling overhead while FTQC costs are driven by physical qubit overhead from code distance and magic states.
A resource-reusing FPGA architecture for GARI-structured message-passing decoding of quantum LDPC codes with correlated errors achieves 596 ns average latency and 6x lower resource use than prior GARI hardware on a VCU19P device.
Lottery BP adds randomness to belief propagation decoding and uses syndrome voting to achieve far higher accuracy on topological quantum codes while reducing reliance on expensive global decoders.
A teleportation-based parallelization architecture for neutral-atom quantum error correction delivers up to 3x speedup over extractor methods at fixed space cost and enables simulated quantum advantage at 11,495 atoms and 15-hour runtime.
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.
GeneCS compiler reduces ancillary qubits and checks by over 85% on average for single- and cross-code logical operations on stabilizer codes while preserving error rates and scaling to over 10,000 qubits.
citing papers explorer
-
Encrypted Neural Networks without Overflows
Introduces formal verification to compute certified neuron range bounds for CKKS-encrypted neural networks, eliminating overflow failures that previously reached 47%.
-
Estimating The Energy Consumption of Quantum Computing from A Full System Aspect
A full-system energy model shows NISQ quantum simulations dominated by error mitigation sampling overhead while FTQC costs are driven by physical qubit overhead from code distance and magic states.
-
A Scalable FPGA Architecture for Real-Time Decoding of Quantum LDPC Codes Using GARI
A resource-reusing FPGA architecture for GARI-structured message-passing decoding of quantum LDPC codes with correlated errors achieves 596 ns average latency and 6x lower resource use than prior GARI hardware on a VCU19P device.
-
Lottery BP: Unlocking Quantum Error Decoding at Scale
Lottery BP adds randomness to belief propagation decoding and uses syndrome voting to achieve far higher accuracy on topological quantum codes while reducing reliance on expensive global decoders.
-
Architecting Early Fault Tolerant Neutral Atoms Systems with Quantum Advantage
A teleportation-based parallelization architecture for neutral-atom quantum error correction delivers up to 3x speedup over extractor methods at fixed space cost and enables simulated quantum advantage at 11,495 atoms and 15-hour runtime.
-
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.
-
GeneCS: Synthesizing Resource-Efficient Code Surgery for Arbitrary Quantum Stabilizer Codes
GeneCS compiler reduces ancillary qubits and checks by over 85% on average for single- and cross-code logical operations on stabilizer codes while preserving error rates and scaling to over 10,000 qubits.