IEEE Transactions on Cloud Computing最新文献

{"title":"SNR-LDM: An Efficient SNR-Guided Latent Diffusion Model for Generative AI Services Over Dynamic Wireless Networks","authors":"Xinfeng Deng;Li Zhou;Canpu Liu;Haitao Chen;Nan Li;Dongtang Ma","doi":"10.1109/TCC.2026.3674604","DOIUrl":"https://doi.org/10.1109/TCC.2026.3674604","url":null,"abstract":"The proliferation of generative AI services, from cloud-based synthesis to on-device content creation, is increasingly bottlenecked by the need for efficient communication over dynamic wireless channels. However, deploying these models at the network edge is impeded by two fundamental challenges, namely the weak coupling between the model and physical channel conditions and the prohibitive computational latency of diffusion-based inference. Existing approaches often treat diffusion as a static module trained at a fixed noise level and indexed by abstract timesteps without physical interpretation, which yields suboptimal performance under time-varying channels. To address this, we propose an signal-to-noise ratio guided latent diffusion model (SNR-LDM). The diffusion process is reparameterized with a physically interpretable mapping between denoising timesteps and channel SNR, aligning the denoising trajectory with the channel state and enabling SNR-adaptive inference. To enhance semantic fidelity, we introduce multimodal guidance that fuses textual and visual prompts to steer content generation. We further develop two inference schemes, namely a dynamic multi-step procedure for highest reconstruction quality and a single-step analytic inversion for ultra-low latency, which makes deployment on resource-constrained edge devices feasible. Experiments show that the proposed model achieves about 4 dB higher PSNR than adaptive baselines and yields up to 8.2% lower LPIPS than diffusionbased benchmarks. The framework links large-scale generative modeling with the communication-constrained network edge and enables robust and efficient deployment of generative AI services.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"850-861"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Device-Bind Key-Storageless IP Protection for Cloud-AI Models via Permutational Diffusional PUF","authors":"Qianqian Pan;Mianxiong Dong;Kaoru Ota;Jun Wu","doi":"10.1109/TCC.2026.3667832","DOIUrl":"https://doi.org/10.1109/TCC.2026.3667832","url":null,"abstract":"With powerful cloud computing capacities, machine learning as a service (MLaaS) framework provides intelligent services and well-trained artificial intelligence (AI) models by clouds for resource-constrained end devices. However, there are AI model leakage and illegal abuse issues during model transmission and deployment. Existing mainstream protection methods face the following problems: (i) The watermark-based methods only provide passive verification afterward rather than active protection. (ii) Encryption-based methods are low efficiency in computation and low security in key storage. (iii) Existing methods are not device-bind without the ability to avoid illegal abuse issues. To deal with these problems, we propose a device-bind and key-storageless cloud-AI model intellectual property (IP) protection mechanism. First, a physical unclonable function (PUF) and permute-diffusion encryption empowered cloud-AI model protection framework is proposed, including the PUF-based secret key generation and the geometric-value transformation-based weights encryption. Second, we design an Anderson PUF-based key generation protocol to generate device-bind robust secret keys. Third, a permutation and diffusion-based intelligent model weights encryption/decryption method is proposed for effective cloud-AI model protection, where chaos theory is utilized to convert PUF-based secret keys to encryption/decryption keys. Finally, experimental evaluation demonstrates the effectiveness and reliability of the proposed intelligent model IP protection mechanism.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"593-608"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized Post-Quantum Attribute-Based Logging for Real-Time and Tamper-Evident Cloud Forensics","authors":"Somchart Fugkeaw;Neeranuch Jitkhajornwanich;Piroon Mongkolchukaie;Natapat Rouengsamai;Nutkamol Pornpinyamad","doi":"10.1109/TCC.2026.3681599","DOIUrl":"https://doi.org/10.1109/TCC.2026.3681599","url":null,"abstract":"Secure audit logging is essential for cloud forensics, yet existing schemes suffer from fundamental limitations. Classical hash-chaining, pairing-based, and RSA/ECC-based logging lose evidential validity under key compromise and quantum attacks, while blockchain-assisted approaches rely on pre-quantum primitives and periodic verification, leaving temporal windows exploitable by insiders. This paper presents <i>Post-Quantum Attribute-Based Logging (PQ-ABL)</i>, a quantum-resilient forensic logging framework with continuous integrity assurance. PQ-ABL employs lattice-based CP-ABE to enforce fine-grained, post-quantum access control, while log payloads are efficiently protected using AES-GCM. Integrity is achieved through an epoch-driven verification model that anchors a single Merkle root per epoch on the blockchain, enabling linear-time <inline-formula><tex-math>$O(N)$</tex-math></inline-formula> full-epoch validation, constant-time <inline-formula><tex-math>$O(1)$</tex-math></inline-formula> local record consistency checking after epoch validation, and <inline-formula><tex-math>$O(log N)$</tex-math></inline-formula> standalone record membership verification, without requiring per-record authentication proofs during epoch validation. The key contribution is an integrity design that decouples post-quantum authorization from verification cost, eliminating forensic blind spots inherent in periodic anchoring. Security analysis proves confidentiality and integrity under standard lattice hardness assumptions. Experimental results show that PQ-ABL reduces verification latency by 31.8% and computation cost by 38.6% compared with existing post-quantum and blockchain-based logging schemes.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"1098-1114"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dependency-Aware Microservice Deployment Optimization via Neural Heuristic Learning","authors":"Hulin Nie;Xiangguo Zhao;Xin Bi;Xin Yao;Junjie Zhou;Ye Yuan","doi":"10.1109/TCC.2026.3680335","DOIUrl":"https://doi.org/10.1109/TCC.2026.3680335","url":null,"abstract":"Microservice deployment should consider dependency constraints and resource requirements while minimizing deployment costs. There are various dependencies among microservices, and such intricate dependencies bring great difficulties to efficient deployment. Despite significant progress, existing deep learning-based methods are not expressive enough to capture the complexity of microservice dependencies. Meanwhile, metaheuristic methods encode such dependencies into problem-specific heuristics through explicit formulae, yet such formulations remain static and inherently limited. This paper addresses these issues by formulating the microservice deployment problem (MSDP) as a variable-sized bin packing problem. We first introduce a heterogeneous graph neural network to effectively represent the complex dependencies of MSDP. Based on this representation, we propose a novel reinforcement learning policy to design heuristics without the need to derive explicit formulae. Guided by the learned heuristics, we further devise a parallel ant colony optimization algorithm to accelerate solution construction. Experimental results from three representative microservice applications demonstrate that our method obtains near-optimal solutions while significantly outperforming the state-of-the-art methods in computational efficiency.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"1038-1054"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy-Aware Incentive Design for Federated Crowdsourcing via Combinatorial Multi-Armed Bandits","authors":"Chenchen Lin;Wenhao Yuan;Edith C. H. Ngai;Xuehe Wang","doi":"10.1109/TCC.2026.3671380","DOIUrl":"https://doi.org/10.1109/TCC.2026.3671380","url":null,"abstract":"Federated crowdsourcing has emerged as a promising paradigm for collaboratively solving learning tasks over mobile edge devices, enabling decentralized model training without direct data uploading. However, conventional federated crowdsourcing systems largely overlook two fundamental challenges: (i) the lack of effective incentive mechanisms under unknown participant quality, (ii) the risk of privacy leakage from model uploading. In this paper, we propose an incentive mechanism for federated crowdsourcing based on the Stackelberg game considering <inline-formula><tex-math>$rho$</tex-math></inline-formula>-zero-concentrated differential privacy and <u>C</u>ombinatorial <u>M</u>ulti-<u>A</u>rmed <u>B</u>andit mechanism, called <i>FedCMAB</i>, to tackle the client selection problem with unknown quality and incentive design while preserving confidential information. We model the interaction between the server and clients as a Stackelberg game, where the server dynamically selects a subset of clients and designs rewards to minimize the cost while each client strategically determines its privacy budget to maximize its individual utility. We theoretically establish the existence of the Stackelberg Nash equilibrium. Next, we leverage the combinatorial multi-armed bandit (CMAB) method to learn optimal client selection strategies with provable regret guarantees and derive an upper bound on the cumulative regret of the proposed mechanism. Moreover, we conduct a rigorous Price of Anarchy (PoA) analysis to quantify the efficiency gap between the decentralized equilibrium induced by self-interested clients and the socially optimal solution. Our analyses demonstrate that conventional incentive-agnostic strategy can lead to an unbounded PoA, resulting in severe efficiency loss. In contrast, our <i>FedCMAB</i> framework provably bounds the PoA by a finite constant. Extensive experimental results on multiple datasets demonstrate that <i>FedCMAB</i> consistently outperforms state-of-the-art baseline methods on both independent and identically distributed (IID) and non-IID data.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"715-730"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cinergy: Deterministic Power Monitoring for Carbon Accounting in the Cloud","authors":"Pierre Jacquet;Camille Coti;Marcos Dias De Assunção;Romain Rouvoy","doi":"10.1109/TCC.2026.3674370","DOIUrl":"https://doi.org/10.1109/TCC.2026.3674370","url":null,"abstract":"Cloud providers now commonly offer tools to monitor the environmental impact of hosted services, aiming to inform customers about the carbon footprint of their infrastructures. A significant share of this impact arises from the power consumption of servers. To allocate server-related emissions, these methodologies typically rely on resource-quantity–based attribution and do not account for the effective usage of virtual resources. We demonstrate that resource usage can drastically affect carbon estimations. This article proposes a framework, called <sc>Cinergy</small>, to standardize how cloud providers integrate the power consumption of virtual resources into their carbon calculators. It defines a baseline to deterministically assess the power consumption of a provisioned <italic>Virtual Machine</i> (VM)—i.e., the same usage should yield the same power estimate—while still accounting for consolidation gains enabled by virtualization. Our approach, constructed and evaluated empirically, achieves high precision, with a mean absolute error of 6.6% across various hardware. Using metrics collected from cloud providers, we reveal the impact of instance type on energy efficiency, with differences reaching 85% for the same VM size. We also show that quantity-based carbon accounting methodologies can drastically underestimate actual CO₂ emissions—by up to a factor of three.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"822-833"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AoI-Aware Collaborative Data Caching in IIoT: A Multi-Agent Reinforcement Learning-Based Approach","authors":"Bingtao Kang;Kai Peng;Shangguang Wang;Xiaolong Xu;Victor C. M. Leung","doi":"10.1109/TCC.2026.3666885","DOIUrl":"https://doi.org/10.1109/TCC.2026.3666885","url":null,"abstract":"To cope with the challenges of the rapid growth of Industrial Internet of Things devices, deploying cache servers (CS) at the edge of the network becomes a promising solution. The cache node (CN) can reduce request latency and the traffic load on backhaul link by pre-caching relevant data generated by sensors. However, the storage resources of CSs are limited, and select the appropriate data item to cache is a critical issue for improving efficiency. In addition, we introduce the Age of Information (AoI) to describe the freshness of cached data. However, increasing the freshness of data through frequent caching updates could result in increased energy consumption of sensor. In this paper, we study the caching problem of multiple CNs, and further model the problem as a multi-agent Markov Decision Process to minimize long-term request latency, AoI, and energy consumption. Furthermore, to solve this problem, we propose a variant of the Soft Actor-Critic-based multi-agent caching algorithm. Finally, experiments show that the proposed algorithm can converge to a better caching strategy and has better performance in multiple objectives than existing algorithms.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"565-578"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy-Preserving Cross-Cloud LDoS Threat Identification via Labelled-Threshold Private Set Intersection","authors":"Xinrui Zhang;Rongxing Lu;Pincan Zhao;Yunguo Guan;Suprio Ray","doi":"10.1109/TCC.2026.3675155","DOIUrl":"https://doi.org/10.1109/TCC.2026.3675155","url":null,"abstract":"Industrial Internet of Things (IIoT) systems in sectors like manufacturing, energy, and healthcare are increasingly deployed in cloud-assisted operational environments, where network telemetry and security analytics are routinely processed in the cloud. However, these systems remain highly vulnerable to cyber threats from shared threat actors. Among these, low-rate Denial of Service (LDoS) attacks, marked by subtle periodic traffic patterns, are particularly challenging to detect when analyzed in isolation. Cross-organization collaborative detection across cloud platforms can improve identification accuracy, but sharing threat intelligence risks exposing sensitive operational information. To tackle this challenge, we propose Labelled-Threshold Private Set Intersection (LT-PSI), a cryptographic framework that allows two organizational clouds to securely identify common elements whose associated label vectors satisfy a similarity threshold, without revealing any additional data. Our LT-PSI protocol introduces an innovative combination of position encoding, Diffie-Hellman Oblivious Pseudorandom Functions (DH-OPRF), and Bloom filters, effectively transforming threshold-based label similarity matching into efficient and privacy-preserving set membership tests. Particularly, our protocol achieves sublinear online complexity and is well-suited for cloud execution, integrating an adaptive early termination strategy that significantly reduces the number of OPRF invocations. We provide formal security proofs under the semi-honest model and validate the protocol through extensive experiments across diverse similarity thresholds and dataset sizes. Results show that LT-PSI is significantly more efficient than brute-force threshold matching while preserving privacy. The framework naturally supports cloud-to-cloud collaborative security analytics and generalizes to broader cloud and edge threat intelligence scenarios requiring private, threshold-based feature matching.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"877-888"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy-Enhanced Federated Prompt Tuning Against Backdoor Attack","authors":"Guanghui He;Yanli Ren;Gang He;Guorui Feng;Xinpeng Zhang","doi":"10.1109/TCC.2026.3660272","DOIUrl":"https://doi.org/10.1109/TCC.2026.3660272","url":null,"abstract":"With the rapid development of large language models, the fine-tuning of downstream tasks has become a key problem. As a new learning paradigm, prompt learning can greatly reduce the number of updated parameters and effectively reduce the communication cost in federated learning scenarios by freezing the pre-trained model and fine-tuning soft prompt parameters. However, for the federated prompt tuning, the local prompt usually contains the user’s personal information, and the text input of the user are easily leaked through the aggregation directly on the server. Meanwhile, the soft prompt is vulnerable to poisoning attacks launched by malicious users (such as backdoor). For the above problems, this article proposes a privacy-preserving federated prompt fine-tuning against poisoning attacks. Specifically, we use homomorphic encryption to ensure the confidentiality of local prompts, and aggregate prompts under ciphertext to generate global prompts. Second, the proposed mechanism of backdoor detection is used to judge whether the prompt contains backdoors to resist the malicious attacks in the form of ciphertext. Both local and global prompts are invisible to the server during the entire training process. Finally, theoretical analysis and experimental results show that the accuracy error between the plaintext domain and the ciphertext domain is controlled within 2%-5% under backdoor attack, which effectively enhances the robustness of the model.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"463-474"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"D2ARL: A Dual Dynamic Attention-Driven Reinforcement Learning Approach for Revenue-Optimized Virtual Network Embedding","authors":"Kunming Jin;Zichen Wang;Wen Xu;Hongwei Du","doi":"10.1109/TCC.2026.3664096","DOIUrl":"https://doi.org/10.1109/TCC.2026.3664096","url":null,"abstract":"With the rapid advancement of the Internet of Things and 5G technologies, edge computing has emerged as a vital paradigm for supporting real-time processing and low-latency applications. At the core of edge computing lies Virtual Network Embedding (VNE), whose resource allocation efficiency directly influences both service quality and revenue generation in edge environments. Recent research has identified reinforcement learning (RL) as a promising approach to enhance the VNE process. However, most existing RL-based methods overlook the potential of attention mechanisms, which can help agents better understand complex network topologies and thereby improve embedding performance. To address this gap, we propose a novel algorithm, D2ARL (Dual Dynamic Attention-driven Reinforcement Learning), which adaptively captures the dynamic characteristics of both physical and virtual networks through a dynamic attention mechanism. D2ARL is built on a sequence-to-sequence (seq2seq) architecture, leveraging dynamic attention in the encoder to capture local features of the networks, and in the decoder to extract globally fused features. Experimental results show that D2ARL outperforms state-of-the-art methods across various network environments. It achieves higher overall benefits and demonstrates stable performance under diverse conditions. Notably, D2ARL improves long-term average revenue by 14.5% compared to the best-performing existing method.","PeriodicalId":13202,"journal":{"name":"IEEE Transactions on Cloud Computing","volume":"14 2","pages":"537-550"},"PeriodicalIF":5.3,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}