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
In many advanced recommender systems (e.g., GNN-based), local smoothing mechanisms would distill collaborative signals but could inadvertently amplify targeted data poisoning threats. Existing defenses predominantly relied on rigid binary filtration strategies. However, such structural deletion of suspicious nodes often compromises graph connectivity, leading to a severe robustness-fidelity dilemma. To fill this gap, we propose SiPo (Silencing the Poison), a novel framework that shifts the paradigm from node removal to gradient silencing. SiPo leverages unsupervised granular ball computing to adaptively capture adversarial topological micro-clusters within the feature space. Subsequently, it geometrically collapses high-risk nodes towards a non-informative singularity via a global gravity gating mechanism. This operation blocks the backpropagation path of malicious gradients, effectively suppressing attacks while preserving the collaborative signals of normal users. Theoretical analysis confirms that SiPo enforces a compression of the local Lipschitz constant. Furthermore, extensive experiments on four public datasets demonstrate that SiPo not only significantly reduces attack success rates but also consistently improves recommendation performance. The implementation code is available at: https://github.com/KREML0/SiPo.
Yunmeng Zhao, Jun Shen, Shenbao Yu et al.· Proceedings of the 32nd ACM...· 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
In many advanced recommender systems (e.g., GNN-based), local smoothing mechanisms would distill collaborative signals but could inadvertently amplify targeted data poisoning threats. Existing defenses predominantly relied on rigid binary filtration strategies. However, such structural deletion of suspicious nodes often compromises graph connectivity, leading to a severe robustness-fidelity dilemma. To fill this gap, we propose SiPo (Silencing the Poison), a novel framework that shifts the paradigm from node removal to gradient silencing. SiPo leverages unsupervised granular ball computing to adaptively capture adversarial topological micro-clusters within the feature space. Subsequently, it geometrically collapses high-risk nodes towards a non-informative singularity via a global gravity gating mechanism. This operation blocks the backpropagation path of malicious gradients, effectively suppressing attacks while preserving the collaborative signals of normal users. Theoretical analysis confirms that SiPo enforces a compression of the local Lipschitz constant. Furthermore, extensive experiments on four public datasets demonstrate that SiPo not only significantly reduces attack success rates but also consistently improves recommendation performance. The implementation code is available at: https://github.com/KREML0/SiPo.
Yunmeng Zhao, Jun Shen, Shenbao Yu et al.· Proceedings of the 32nd ACM...· 0 citations
Spatial domain identification in spatial transcriptomics (ST) partitions a tissue section into spatially coherent regions with distinct transcriptional programs. Recent graph-based approaches construct a spatial neighborhood graph and/or an expression-similarity graph and perform unsupervised domain identification with GNN encoders or graph-regularized embeddings. However, dropout and boundary mixing make neighborhood reliability highly non-uniform across space, so fixed graphs can propagate signals across true boundaries and blur domains, motivating unit-wise multi-view fusion and topology refinement. We propose GatorTrio, a topology-refined tri-view graph learning framework that adaptively fuses views per unit via an interaction-aware sparse Mixture-of-Experts (MoE) router. GatorTrio constructs three complementary graphs: (i) an attention-induced expression-affinity graph, (ii) a dropout-aware expression-similarity graph, and (iii) a spatial kNN neighborhood graph. A parameter-sharing GNN encoder encodes each graph, and the router fuses the resulting view-specific embeddings; view dropout and learnable missing-view tokens improve robustness to noisy and missing views. We refine topology through self-training by pruning pseudo-label–inconsistent inter-cluster edges and re-encoding on the refined graphs. Training combines bidirectional topology-informed contrastive learning between expression views with spatially anchored prototype alignment that matches expression-view centroids to perturbed spatial prototypes under a curriculum warm-up. Experiments on diverse ST benchmarks show consistent improvements over ten representative baselines and support downstream biological analyses.
Zhenhao Zhang, Jun Shen, Jiang Bian et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
