TL;DR
PrivSynth is proposed, a framework that quantifies multiple privacy risks and integrates it into the control ob-jective, and achieves better utility and stronger privacy protection than state-of-the-art methods.
Federated Learning (FL) avoids centralizing raw data, but server-side access to per-client updates still creates a significant privacy risk because gradients can leak sensitive information through inversion and related attacks. A common defense is client-level Differential Privacy (DP), which reduces attack fidelity by...
Federated learning is appealing for privacy-sensitive network systems, yet its practical deployment remains hindered by the following three recurring challenges: (1) client drift under non-IID data, (2) vulnerability to corrupted updates, and (3) the communication cost of repeated model exchange. Most existing approach...
This paper investigates whether state-of-the-art deep learning trajectory generators can be adapted to satisfy differential privacy (DP) while retaining usable utility, and introduces RouteMIA, the first closed-box membership inference attack tailored to synthetic trajectories.
Gecko is presented, designed to limit this additional risk while retaining a compact encrypted predictor, and formalizes ideal independence and information-preservation conditions as design guidance, then separately evaluate component-reuse extraction attacks.
P2Skill is proposed, a prompt-based skill distillation method in which a local small language model (SLM) autonomously performs decomposition, PII-aware routing, paraphrasing, and reconstruction by following the skill prompts.
CoVeil is proposed, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality, and consistently improves the privacy-utility trade-off over existing baselines by reducing data leakage.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
