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

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 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 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…

This paper introduces a unified threat model and evaluation framework to systematically compare privacy-preserving techniques for distributed learning in IoT systems, highlighting the trade-off betwee…

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…

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 four-phase protocol to enable secure, multi-key homomorphic encryption (xMK-CKKS) aggregation for zero-order Federated Learning over wireless channels without requiring chan…

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…

The paper proposes a scalable, privacy-preserving framework for iris recognition using Fully Homomorphic Encryption (FHE), achieving accuracy comparable to cleartext while identifying the computationa…

The paper reverse-engineers Apple's Private Cloud Compute (PCC) implementation to independently benchmark its model and evaluate its privacy claims, addressing the lack of transparency in Apple's syst…

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 proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

The paper characterizes Homomorphic Encryption (HE) operations on a real-world Processing-In-Memory (PIM) system, demonstrating that while PIM is a viable alternative to CPUs/GPUs, performance is limi…

The paper introduces FHE-DiCSNN, a novel framework that uses the TFHE scheme to enable secure and efficient computation on Spiking Neural Networks (SNNs), achieving high accuracy and fast inference ti…

The paper proposes a Privacy-Preserving Product-Quantization Approximate Nearest Neighbor (PPPQ-ANN) framework that achieves practical performance and strong privacy guarantees for large-scale nearest…

This paper demonstrates the feasibility of running a privacy-preserving inference for the Llama 3 LLM by integrating Post-Quantum Cryptography (PQC) based Lattice-based Fully Homomorphic Encryption (F…

The paper proposes a novel method using fully homomorphic encryption (FHE) to learn causal structures while preserving data privacy, achieving high consistency and practical efficiency.