The paper introduces Sherpa.ai, a multi-party Private Set Union (PSU) protocol that enables privacy-preserving entity alignment for Vertical Federated Learning (VFL) without disclosing shared sample i…

The paper proposes a novel data transformation framework that creates semantically rich, privacy-preserving numeric views of EHR data, enabling large-scale research while provably breaking patient lin…

RootGuard introduces a dependency-aware privacy mechanism that sanitizes private data roots once, ensuring consistent privacy guarantees across multiple multi-turn agent interactions, significantly ou…

The paper proposes FERMI, a method that significantly improves membership inference attacks against tabular diffusion models by leveraging auxiliary relational information available during training, e…

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

The paper introduces Search-Bound Proximity Proofs (SBPP) to close an authorization provenance gap in encrypted geographic search by binding zero-knowledge proofs to specific search sessions for audit…

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 proposes a novel two-stage framework to differentially privatize tables of counts by focusing on preserving the accuracy of the underlying count distribution, introducing the specialized cyc…

The paper proposes a Quantitative Information Flow (QIF) framework to systematically and rigorously compare Local Differential Privacy (LDP) frequency estimation protocols, moving beyond simple $\vare…

GPIR is a GPU-accelerated Private Information Retrieval (PIR) system that significantly boosts throughput by introducing a stage-aware hybrid execution model and optimizing data layouts for modern GPU…

The paper proposes a novel ring-based information-theoretic Private Information Retrieval (itED-PIR) scheme that overcomes the key size and communication overhead limitations of existing field-based A…

The paper proposes a commit-open protocol using SAE feature-trace commitments to detect silent model substitution in hosted Large Language Models, successfully rejecting various sophisticated attacker…

This paper introduces a novel, efficient protocol for training Gradient Boosting Decision Trees (GBDT) on vertically partitioned data held by two mutually distrustful parties while ensuring complete a…

SEAL-Tag is a privacy-preserving runtime environment that mitigates PII leakage in Retrieval-Augmented Generation (RAG) systems by enforcing verifiable evidence aggregation and structured auditing.

The paper introduces Metric-Normalized Posterior Leakage (mPL), an attacker-aligned measure that provides a practical, certifiable privacy guarantee for machine learning systems consumed under joint o…

Gyokuro is a novel Source-assisted Private Membership Testing (SPMT) protocol that uses Trusted Execution Environments (TEEs) to efficiently and privately verify data item existence in large databases…

The paper introduces SPIDER, a novel single-server Private Information Retrieval (PIR) scheme that achieves state-of-the-art communication complexity without requiring specialized server cooperation o…

FedAttr introduces a novel client-level attribution protocol for Federated Learning (FL) that accurately identifies which clients trained on watermarked data while maintaining strong privacy guarantee…

The paper introduces a 'Privacy Guard' framework that simultaneously reduces operational costs and eliminates data leakage risks when using LLMs by optimizing prompts and routing queries to secure mod…