The paper proposes a kernel-based, polynomial approximation of the ReLU activation function to enable the use of non-linear deep learning models, such as LLMs, within the constraints of Homomorphic En…

This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.

The paper provides the first theoretical convergence analysis for machine learning training under fully homomorphic encryption combined with differential privacy, improving efficiency and scalability.

The paper introduces public-decay Homomorphic State Space Models (HSSMs) that enable efficient, high-accuracy sequence inference directly on encrypted data, significantly outperforming existing encryp…

The paper proposes a co-design paradigm, 'Meeting in the Middle,' to make Fully Homomorphic Encryption (FHE) practical for AI inference by optimizing both the cryptographic schemes and the underlying…

This paper provides a comparative analysis and benchmarking of Secure Multi-Party Computation (SMPC) and Fully Homomorphic Encryption (FHE) for machine learning, finding that the optimal choice depend…

This paper provides a comprehensive, system-level comparison of MPC and FHE for Privacy-Preserving Machine Learning (PPML) across various models and environments, moving beyond single-metric latency a…

The paper proposes a novel space switching method to efficiently unify arithmetic and comparison operations within Fully Homomorphic Encryption (FHE) schemes, achieving significant performance improve…

The paper addresses the vulnerability of CKKS-based Fully Homomorphic Encryption (FHE) to overflow attacks by proposing a formal verification technique that guarantees certified bounds on all neuron r…

The paper proposes Independent Vector Evaluation (IVE), a novel method that significantly reduces the computational cost of generating selection vectors for private embedding lookups under Fully Homom…

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…

The paper proposes a novel, optimized sparse matrix multiplication method for fully homomorphic encrypted deep neural networks, achieving up to a 3.0x speedup on AMD GPUs compared to CPU implementatio…

The paper proposes and validates a privacy-preserving framework using Homomorphic Encryption (HE) to train and run Machine Learning models on sensitive data while keeping it encrypted throughout the e…

The paper introduces a unified framework for Quantum Fully Homomorphic Encryption (QFHE) that achieves exponential efficiency improvements by integrating a novel modular arithmetic program (MAP) tailo…

This paper enhances Federated Learning privacy by integrating two key protection mechanisms—masking and RSA encapsulation—into Hybrid Homomorphic Encryption (HHE) to secure against malicious clients.

The paper proposes a multi-ciphertext privacy-preserving framework to efficiently compute high-resolution image gradients using Fully Homomorphic Encryption (FHE) by dividing the large image into smal…

AEGIS is a novel system that significantly improves the scalability of running large, long-sequence Transformer models under Fully Homomorphic Encryption (FHE) on multi-GPU systems by optimizing data…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…