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…

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 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…

Opal is a private memory system for personal AI that maintains high retrieval accuracy and throughput while ensuring data privacy by confining all data-dependent reasoning to a trusted hardware enclav…

The paper proposes a privacy-by-design pipeline for Android malware detection that achieves strong performance by avoiding the collection of sensitive user data entirely.

The paper introduces extsc{Spore}, a novel, training-free, and highly efficient privacy extraction attack that targets sensitive information stored in the memory of LLM agents during inference, outpe…

This survey analyzes the unique security threats posed by complex, multi-agent AI systems and proposes Confidential Computing (CC) using Trusted Execution Environments (TEEs) as a hardware-rooted defe…

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…

This paper evaluates the vulnerability of Fully Homomorphic Encryption (FHE) computation to silent data corruption (SDC) using large-scale fault-injection experiments and theoretical analysis.

The paper introduces EBCC, an OCI-compatible runtime architecture that manages composite confidential-computing workloads by integrating TEE-backed execution into the standard container lifecycle.

MemPrivacy introduces a novel framework that protects sensitive user data in edge-cloud memory systems by replacing private spans with semantically structured placeholders, thereby minimizing data exp…

AgenTEE is a system that enables the secure, confidential execution of complex LLM agent pipelines directly on edge devices by using isolated confidential virtual machines.

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 audits Apple's Differential Privacy framework on macOS and finds multiple implementation bugs and misconfigurations, revealing significant privacy violations in a large percentage of collec…

The paper introduces CCX, a framework that allows existing Intel SGX applications to run on Arm CCA hardware without requiring any source code modifications, thereby improving portability for confiden…

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to…

This paper develops a differential privacy framework to analyze and optimize privacy leakage from AI agent responses that utilize sensitive enterprise data, focusing on deriving optimal generation par…

The paper introduces CIPL, a unified channel-oriented framework, demonstrating that privacy leakage in LLM agents is governed by observable data channels and pipeline interactions, rather than being l…

This paper presents a novel data-free Membership Inference Attack (MIA) that uses gradient inversion on Standard Cell Library Layouts (SCLLs) to reconstruct sensitive hardware images from intercepted…

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.