~ similar to 2606.16809· 20 results
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…
Katharine Daly, Yu Xiao, Zachary Garrett, Brett McLarnon +8 more
The paper presents a next-generation Federated Learning system that provides externally verifiable central Differential Privacy guarantees while improving device coverage and privacy-utility tradeoff.
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 empirically evaluates the effectiveness of Differential Privacy (DP) against Membership Inference Attacks (MIAs) in Federated Learning, demonstrating that a stacking attack strategy can det…
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…
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 corrects the theoretical analysis of DP-SGD by identifying that common implementations, which use batch averaging, result in weaker privacy guarantees than previously reported.
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 proposes Interflow, an algorithm-hardware co-design that improves the efficiency of privacy-preserving machine learning by pipelining correlated randomness generation with online execution.
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 proposes a hashing-based framework using Differential Privacy to generate and release private datastores for retrieval-augmented AI systems, achieving strong privacy with minimal accuracy lo…
This paper identifies side-channel vulnerabilities in Confidential Federated Compute platforms that could bypass differential privacy guarantees, demonstrating how DP can mitigate some of these risks.
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…
The paper proposes FedPower, a novel differentially private cross-silo Federated Learning framework that uses PowerDP to reconstruct and project client updates into a secure low-rank space, effectivel…
Venish Patidar, Dhruv Bindra, Ahmed Darwich, Josh Brown +2 more
This paper proposes a decentralized, confidential computing platform using Intel TDX, ITA, and NVIDIA CC for secure and affordable AI workloads.
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…
CloakLM is a software-only memory-obfuscation framework that protects large language models from model exfiltration attacks.
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 an optimized, end-to-end privacy-preserving framework for vertical federated learning by distributing aggregation roles across multiple servers using secure multiparty computation a…