The paper introduces TrEEStealer, a novel side-channel attack that efficiently steals Decision Trees (DTs) protected within Trusted Execution Environments (TEEs), demonstrating that TEEs fail to provi…

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…

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…

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

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…

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…

VeriX-Anon is a multi-layered framework that provides mathematically verifiable assurance that outsourced data anonymization (k-anonymization) was executed correctly, achieving high detection rates ag…

The paper introduces LATTICE, a novel benchmark for evaluating how well crypto agents assist user decision-making, finding that different agents excel in different specific areas rather than having a…

TAPAS introduces an efficient, asymmetric two-server private aggregation scheme that significantly reduces computational and communication costs for large-scale federated learning compared to existing…

The paper proves that platform-deterministic inference is a necessary and sufficient condition for trustworthy AI, establishing that AI trust fundamentally relies on consistent arithmetic.

The paper introduces Zero-Run privacy auditing, a post-hoc framework that allows for practical differential privacy evaluation of large, deployed models without requiring retraining or controlled data…

This paper provides the first comprehensive Systematization of Knowledge (SoK) on the security aspects of LLM-as-a-Judge (LaaJ) systems, identifying key vulnerabilities and proposing a taxonomy for fu…

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…

TENNOR is a system that enables efficient and private training of wide neural networks in untrusted cloud environments by using doubly oblivious primitives and a novel memory-efficient hashing scheme.

The paper proposes a trustless framework using dual-layer cryptographic commitments to solve the operator-gating problem in blockchain provenance trees, ensuring verifiable user attribution even when…

The paper proposes a confidence-aware, multi-layered Cloud-IDS pipeline that integrates adaptive Q-Learning, Chroma memory, and LLM semantic analysis to enhance detection accuracy and reduce reliance…

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)…

TeeDAO introduces a novel three-layer framework that autonomously organizes and manages multiple heterogeneous Trusted Execution Environments (TEEs) to provide robust, distributed-trust systems with h…

The paper proposes a new evaluation framework showing that, under realistic conditions, Membership Inference Attacks (MIAs) are weak privacy threats, suggesting that relying on them as a primary priva…