~ similar to 2604.17476v1· 20 results
PrivFedTalk introduces a privacy-aware federated framework for personalized talking-head generation by combining a shared diffusion backbone with local LoRA identity adapters and robust aggregation te…
ThermalTap presents the first passive, non-contact side-channel attack that fingerprints virtual reality (VR) applications by analyzing the long-wave infrared (LWIR) thermal radiation emitted by the h…
The paper proposes a Jacobian-guided anisotropic noise reshaping technique to selectively attenuate noise in task-relevant subspaces, significantly enhancing data utility while maintaining Local Diffe…
The paper introduces EvaluatAR, a cross-device evaluation framework that standardizes the testing of bystander Privacy-Enhancing Technologies (PETs) in Augmented Reality (AR) to enable rapid, reproduc…
This paper introduces a garbled-circuit (GC)-based framework for performing secure and privacy-preserving comparison of eye-tracking scanpaths, supporting both two-party and server-assisted configurat…
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…
CloakLM is a software-only memory-obfuscation framework that protects large language models from model exfiltration attacks.
Xueyang Wang, Xihuan Yao, Yanming Xiu, Xin Yi +2 more
This paper identifies a security vulnerability in consumer MR headsets and demonstrates four proof-of-concept attacks.
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)…
This paper introduces an attack, PRIVX, demonstrating that even differentially private (DP) Graph Neural Network (GNN) explanations leak enough structural information to allow an adversary to accurate…
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.
The paper proposes IntraShuffler, a novel privacy-preserving middleware defense that enables gradient shuffling in Heterogeneous Differential Privacy Federated Learning (HDP-FL) systems, significantly…
The paper proposes IntraShuffler, a novel privacy-preserving middleware defense that enables gradient shuffling in Heterogeneous Differential Privacy Federated Learning (HDP-FL) while maintaining the…
Lucas Fenaux, Larris Xie, Aditya Bang, Alex Zhang +2 more
The paper proposes a Public/Private Hybrid Head-VFL (PPHH-VFL) architecture that significantly accelerates secure time-series inference by splitting the model head into efficient public and secure pri…
The paper introduces a differentially private manifold denoising framework that allows noisy, non-private query points to be corrected using sensitive reference data while providing formal $(\varepsil…
The paper presents a complete, moderatorless protocol for playing Werewolf using only ordinary playing cards, eliminating the need for a trusted third party or digital devices.
This paper proposes DataGuard, a hardware-based mechanism to ensure differential privacy in federated learning without trusting a third-party application.
The paper introduces VRSafe, a novel virtual QWERTY keyboard designed to significantly mitigate keystroke inference attacks in virtual reality by introducing false positive keystrokes and incorporatin…
The paper introduces WaveGuard, a frequency-aware, single-pass defense framework that safeguards text-to-image models by injecting structured, imperceptible perturbations into generated images, thereb…
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.