Edge devices handle sensitive user data, raising significant security and privacy concerns when shared with data collectors for downstream learning tasks. One potential solution leverages differentially private generative models, keeping original data on user devices and creating obfuscated variants for transmission. However, this approach presents two challenges: 1) Obfuscated data that closely resembles the original compromises privacy, whereas excessive dissimilarity diminishes its utility. 2) Diverse computing capabilities of edge devices hinder deploying such models across hardware platforms. To address these issues, we first introduce Differential Privacy with Adaptive Clipping and Noise Scaling (DP-ACNS), which dynamically adjusts privacy parameters to better balance privacy and utility than conventional DP training. Next, to overcome deployment challenges, we propose a two-stage Neural Architecture Search (NAS) approach. In Stage 1, we utilize DP-ACNS to centrally train an over-parameterized network on proxy data. Following this, we iteratively apply symmetric pruning with subsequent knowledge distillation to generate pretrained architectures. In Stage 2, we conduct a feedback-driven evolutionary search to identify optimal architectures that meet edge computational constraints, and adapt them via minimal fine-tuning on target devices. Experimental results demonstrate that our approach effectively balances privacy and utility while maintaining performance across diverse computational environments in edge computing.
Adil Sarwar, Yanlong Zhai, Jun Shen et al.· IEEE Transactions on Mobile...· 0 citations
Mobile edge computing (MEC) accelerates Internet of Things (IoT) applications by caching content near end users. However, cached data remains vulnerable to corruption, misleading applications, and eroding user trust. Traditional centralized edge data integrity verification (EDIV) methods adopt challenge-response protocols involving third-party auditors (TPAs), incurring nontrivial computation and communication costs along with privacy concerns. Recent decentralized frameworks leverage federated learning (FL) to train models for initial screening, eliminating TPAs. However, their performance is impeded by computational and data heterogeneity across edge nodes and the substantial overhead of blockchain-based validation. Furthermore, such frameworks exhibit limited precision in localizing corrupted data. To address these challenges, this article introduces the decoupled EDIV (D-EDIV) framework, which explicitly decouples integrity verification into a two-stage mechanism of corruption detection and corruption localization. During Stage 1, D-EDIV executes corruption detection models at edge nodes. A federated adaptation scheme tailors these models to each node’s computational resources and local data distribution. Upon detecting anomalous instances, a fusion strategy correlates network-layer alerts with cached data modification events to generate perblock suspicion scores, prompting the application vendor (AV) to trigger Stage 2. In this stage, the AV conducts targeted localization on potentially corrupted data. In particular, after authenticating data commitments via a digital signature, the AV utilizes suspicion scores to calculate dynamic decision thresholds, guiding Merkle tree traversal and restricting cryptographic validation to high-risk data blocks. Experimental results demonstrate that D-EDIV improves detection accuracy by 3%–12% and reduces computational overhead by $3\times $ – $8\times $ , efficiently achieving fine-grained integrity verification in heterogeneous MEC environments.
Adil Sarwar, Yanlong Zhai, Jun Shen et al.· IEEE Internet of Things Jour...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
