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 an optimized, end-to-end privacy-preserving framework for vertical federated learning by distributing aggregation roles across multiple servers using secure multiparty computation a…

This paper addresses the challenging problem of multi-objective submodular maximization under a cardinality constraint while ensuring differential privacy, proposing novel algorithms with approximatio…

The paper proposes PPRoute, a privacy-preserving LLM routing framework that significantly speeds up secure model selection while maintaining high performance comparable to non-private methods.

The paper models cryptographic hybridization as a Stackelberg game where the defender optimizes algorithm selection against a resource-constrained attacker who performs conditional optimization.

The paper develops a general framework to exactly characterize the composition of mechanisms satisfying multiple differential privacy constraints, extending known results to arbitrary numbers of const…

The paper develops a unified theoretical framework to systematically characterize the optimal privacy-utility trade-off (PUT) and optimal Local Differential Privacy (LDP) channels for general statisti…

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…

This paper demonstrates that the classical discrete Laplace mechanism can be post-processed to create versatile, unbiased estimators for various subexponential functions, making it a preferred choice…

This paper analyzes the performance and explainability requirements of evolutionary algorithms when applied to complex, real-world physics-informed optimization problems, identifying a gap between cur…

SecureRouter is an encrypted routing and inference framework that accelerates secure transformer inference by adaptively selecting the optimal model size based on the encrypted input, achieving a 1.95…

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…

DDP-SA is a novel federated learning framework that combines local differential privacy and secure aggregation to achieve robust, scalable, and highly private model training.

The paper experimentally validates a novel secure two-party computation protocol for running dynamic controllers over secret sharing, demonstrating its feasibility for real-time control systems despit…

This paper analyzes the trade-offs between privacy, efficiency, and targeting precision in aid allocation systems by studying private variants of both individual and unit-level allocation strategies.

The paper demonstrates that by introducing carefully designed correlations among locally added noise variables, local differential privacy mechanisms can achieve an estimation cost matching the optima…

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a light…

The paper introduces a Variational Encrypted Model Predictive Control (VEMPC) protocol that enables online MPC execution using only encrypted polynomial operations, eliminating the need for intermedia…

The paper proposes Context-aware Metric Differential Privacy (C-mDP), a framework that improves vehicle location privacy by modeling temporal dependencies, achieving higher data utility than standard…

This paper proposes a comprehensive federated learning workflow that enhances privacy and robustness by integrating personalized differential privacy budgets and client drift detection, achieving bett…