Introduction Recently, federated learning has been successfully applied in fields related to cyber-physical-social systems (CPSSs), owing to its ability to harness decentralized clients for training a global model while ensuring data privacy. The existing methods encounter two main obstacles, namely, the statistical distribution heterogeneity [non-independent and identically distributed (non-IID)] among clients and the scarcity of labeled data.Methods In this article, we propose a federated semi-supervised learning (FSSL) model under the label-at-server scenario, denoted as FedAlign, which is tailored for distributed cyber-physical-social systems. FedAlign adopts a dual knowledge distillation framework to train the global model. On the client side, FedAlign integrates contrastive learning, knowledge distillation, and pseudo-labeling technology to train local models. The goal is to ensure that global knowledge is not overlooked while enabling clients to learn local knowledge. Meanwhile, on the server side, FedAlign utilizes maximum mean discrepancy to generate a global feature space. Based on the generated feature space, FedAlign employs a knowledge distillation mechanism and supervised learning to aggregate local knowledge and update the global model.Results Two classic datasets, CIFAR-10 and Fashion-MNIST, are used to evaluate the performance of FedAlign. The experimental results demonstrate that FedAlign outperforms traditional federated semi-supervised learning models.Discussion The integration of feature alignment and knowledge enables balancing local knowledge learning and aggregation of global model. As a consequence, FedAlign enhances the adaptability and generalization ability of the global model in CPSSs.

Source Code Model (SCM) aims to learn the proper embeddings from source codes, demonstrating significant success in various software engineering or security tasks. The recent explosive development of Large Language Model (LLM) extends the family of SCMs, bringing LLMs for code (LLM4Code) that revolutionize development workflows. Investigating different kinds of SCM vulnerability is the cornerstone for the security and trustworthiness of AI-powered software ecosystems, however, the fundamental one, transferable vulnerability, remains critically underexplored.Existing studies neither offer practical ways, i.e. require access to the downstream classifier of SCMs, to produce effective adversarial samples for adversarial defense, nor give heed to the widely used LLM4Code in modern software development platforms and cloud-based integrated development environments.Therefore, this work systematically studies the intrinsic vulnerability transferability of both traditional SCMs and LLM4Code, and proposes a victim-agnostic approach to generate practical adversarial samples. We design a Hierarchical Adaptive Bandit-based Intelligent method for Transferable Attack (HABITAT), consisting of a tailored perturbation-inserting mechanism and a hierarchical Reinforcement Learning (RL) framework that adaptively selects optimal perturbations without requiring any access to the downstream classifier of SCMs. Furthermore, an intrinsic transferability analysis of SCM vulnerabilities is conducted, revealing the potential vulnerability correlation between traditional SCMs and LLM4Code, together with fundamental factors that govern the success rate of victim-agnostic transfer attacks.These findings of SCM vulnerabilities underscore the critical focal points for developing robust defenses in the future.Experimental evaluation demonstrates that our constructed adversarial examples crafted based on traditional SCMs achieve up to 64% success rates against LLM4Code, representing over 15% improvement over the existing state-of-the-art method.

Federated semi-supervised learning (FSSL) has garnered substantial attention for enabling collaborative global model training across multiple clients to address the scarcity of labeled data and to preserve data privacy. However, FSSL is plagued by formidable challenges stemming from cross-client data heterogeneity, as existing methods fail to achieve effective fusion of feature subspaces across distinct clients. To address this issue, we propose a novel FSSL framework, named FedSPQR, which is explicitly tailored for the label-at-server scenario. On the server side, FedSPQR adopts subspace clustering and fusion method based on the Grassmann manifold to construct a unified global feature space, which is further leveraged to refine the global model. On the client side, the pre-established global feature space acts as a benchmark for aligning the local feature subspaces. Based on the aligned local feature subspaces, integrating self-supervised learning with knowledge distillation facilitates effective local learning to alleviate local bias caused by data heterogeneity. Extensive experiments on two standard public benchmarks confirm that FedSPQR outperforms state-of-the-art (SOTA) baselines by a significant margin.

Website Fingerprinting (WF) aims to identify users' visited websites from encrypted traffic traces, disabling the anonymity of encrypted communication like the Tor network. It is practical to use historically labeled (source) data, e.g., public datasets, to pre-train a WF model, and then collect few incoming (target) data to re-train this model within a low cost. Unfortunately, there is always a considerable difference of latent feature distributions between the source and target data (i.e., the cross-domain problem) and an inevitable bias of feature distribution caused by a limited volume of target data (i.e., the biased distribution problem). Although current FewShot Learning-based WF (FSWF) methods achieve satisfactory performance on the efficient establishment, they lack crossdomain transferability, and meanwhile, are unable to alleviate the distribution bias. In this paper, we first systematically analyze the cross-domain problem among different domains of traffics, revealing the ubiquity and dominant factors of it. To mitigate the cross-domain and biased distribution problems, we propose a Distribution Calibrated Website Fingerprinting (DCWF) method that incorporates a two-stage distribution calibration process and a tailored circle network. In the two-stage calibration process, we first devise a re-modeling mechanism capturing the information distribution of the target domain to extract representative features, and then design a calibration process to adjust the biased distribution of the target domain. Subsequently, a tailored circle network is proposed to reduce the noise caused by the calibration process. Finally, extensive experiments are conducted and the results demonstrate the superiority of our DCWF over comparisons under both close-world and open-world settings.

In this paper, we propose a remote attestation approach based on multiple verifiers named CARE. CARE aims to enhance the practicality and efficiency of remote attestation while addressing trust issues within environments involving multiple stakeholders. Specifically, CARE adopts the concept of swarm verification, and employs a circular collaboration model with multiple verifiers to collect and validate evidence, thereby resolving trust issues and enhancing verification efficiency. Moreover, CARE introduces a meticulously designed filtering mechanism to address the issue of false positives in verification outcomes non-invasively. CARE utilizes a multiway tree structure to construct the baseline value library, which enhances the flexibility and fine-grained management capability of the system. Security analysis indicates that CARE can effectively resist collusion attacks. Further, detailed simulation experiments have validated its capability to convincingly attest to the trustworthiness of the dynamically constructed environment. Notably, CARE is also suitable for the remote attestation of large-scale virtual machines, achieving an efficiency 9 times greater than the classical practice approach. To the best of our knowledge, CARE is the first practical solution to address inaccuracies in remote attestation results caused by the activation of Integrity Measurement Architecture (IMA) at the application layer.

The Internet of Vehicles (IoV) is an emerging technology that enhances traffic security and transportation efficiency by enabling smart, connected vehicles to communicate and exchange messages. IoV networks are a key component of intelligent transportation system (ITS) in smart cities. However, these networks are vulnerable to malicious vehicles that disseminate deceptive messages or impersonate legitimate entities, which compromises network security. These adversarial vehicles jeopardize the integrity and availability of the IoV network, exposing it to various security threats, including both insider and outsider attacks. Such attacks can severely undermine the trust and reliability of communication between legitimate vehicles. To address these challenges, we propose TMSU-IoV, a uncrewed aerial vehicles (UAVs)-assisted trust management scheme that integrates identity authentication technique and trust evaluation mechanism to ensure secure communication of connected vehicles in IoV networks. To counteract outsider attacks, we introduce a certificateless signature-based authentication method that guarantees the authenticity of messages exchanged between vehicles and UAVs. To mitigate insider threats, we propose a Quality of Service (QoS)-based trust evaluation mechanism. This mechanism consists of a prior trust evaluation method and a posterior trust evaluation method, designed to enhance both the credibility and timeliness of trust evaluation for connected vehicles. Formal security analysis confirms that the TMSU-IoV effectively resists a variety of insider and outsider attacks. Performance evaluation experiments demonstrate that the TMSU-IoV can accurately assess the trust levels of connected vehicles and outperform traditional trust evaluation methods.

In the industrial ecosystem, both the manufacturing and edge clouds collaborate via virtualisation technology, playing a crucial role in the efficient aggregation and processing of vast data from endpoints, offering computational and analytical support for enhanced decision-making in all industrial operations. Consequently, ensuring the reliability of virtualised manufacturing environments is paramount. Remote attestation offers a viable solution, however, current schemes are plagued by inefficiencies and privacy leakage issues. To address these concerns, we propose an efficient remote attestation approach. The approach actively conceals sensitive industrial information in measurement logs by using a hash algorithm, thereby preventing privacy breaches. Furthermore, it streamlines log entries with a log compression algorithm, enhancing remote verification efficiency in the industrial information architecture. Extensive experiments were conducted in an authentic cloud environment by applying this approach across both mesh and hierarchical remote verification structures, reducing time overhead by approximately 81.32%. Additionally, it marginally impacts server performance with only a 1.49% reduction. The results affirm the proposed approach's exceptional efficacy in decreasing verification durations and mitigating remote verification attacks, demonstrating its promising utility and feasibility in the intelligent industrial platform.

The synergy and convergence of edge, cloud and Internet of Things (ECoT) has increasingly become a promising service paradigm. It provides a wide variety of benefits for IoT applications deployed at the edge of the network to serve end users. However, the open connectivity, complex heterogeneity, and flexible mobility of the ECoT environment bring the challenging issues of service level agreement (SLA) compliance to various IoT applications. To this end, a dynamic QoS-aware based SLA compliance verification model is proposed. Considering the dynamic uncertainty of QoS attributes of edge service in ECoT context, the model presents a QoS consistency detection method to enhance its fault tolerance for QoS violation. Moreover, the model adopts an objective weight assignment method for dynamic QoS to improve the accuracy of SLA compliance verification. Finally, the simulation experiments conducted using a real-world dataset show that our scheme can effectively ensure SLA compliance of edge enabled cloud service for IoT applications.

Unmanned aerial vehicles (UAVs) assisted mobile edge computing (MEC) is an emerging network architecture that has been considered as a promising transformative service paradigm. It enhances the coverage of intelligent mobile communication network and promotes the rapid development of a wide range of internet of things (IoT) applications. However, the ever-increasing data transmission demands given rise by these IoT applications based on MEC have posed significant challenges to the service of quality (QoS) guarantee of UAVs-assisted MEC (UAVs-MEC) network. To address the issue, we propose a novel UAVs-MEC QoS guarantee scheme that can enhances the reliability of IoT applications in UAVs-MEC network. Specifically, a dynamic QoS-aware based service level agreement (SLA) compliance verification model for MEC service is proposed in the scheme. It can monitor and detect the consistency of dynamic QoS of IoT applications through UAVs to ensure the continuous SLA compliance of service provided by MEC. Additionally, an objective weight assignment method and an adaptive update method are presented to improve the accuracy and scalability of the scheme. Finally, the simulation experiments conducted using a real-world dataset show that the proposed scheme can efficiently and effectively verify the SLA compliance of MEC service for guaranteeing QoS of IoT applications in UAVs-MEC context while outperforms other existing SLA violation detection methods.

Due to the need for massive device connectivity, low communication latency, and various customizations in 6G architecture, a distributed cloud deployment approach will be more relevant to the space-air-ground-sea integrated network scenario. However, the openness and heterogeneity of the 6G network cause the problems of network security. To improve the trustworthiness of 6G networks, we propose a trusted computing-based approach for establishing trust relationships in multi-cloud scenarios. The proposed method shows the relationship of trust based on dual-level verification. It separates the trustworthy states of multiple complex cloud units in 6G architecture into the state within and between cloud units. Firstly, SM3 algorithm establishes the chain of trust for the system’s trusted boot phase. Then, the remote attestation server (RAS) of distributed cloud units verifies the physical servers. Meanwhile, the physical servers use a ring approach to verify the cloud servers. Eventually, the centralized RAS takes one-time authentication to the critical evidence information of distributed cloud unit servers. Simultaneously, the centralized RAS also verifies the evidence of distributed RAS. We establish our proposed approach in a natural OpenStack-based cloud environment. The simulation results show that the proposed method achieves higher security with less than a 1% system performance loss.

Green edge-assisted unmanned aerial vehicle (eUAV) network is an emerging network architecture enhanced with the energy efficiency technology that provides an ubiquitous communication for air and ground. It is considered a promising technology that can maintain a balance between a clean environment and a rich human life to build a sustainable world. However, the security issues exposed by UAVs have raised concerns about the trust and security for adopting eUAV network for communication. To this end, a trust assessment as a service (TaaS) scheme for secure communication of green eUAV network is proposed. The TaaS can effectively collect the valid data of UAVs about diverse and dynamic quality of service (QoS) attributes related to energy efficiency. To predict the actual data of UAVs about QoS attributes in the real green eUAV environment, an service level object calibration method is presented in TaaS. In addition, to accurately obtain the trust level of UAVs in the eUAV network, TaaS presents a trust level assessment method integrated the interval multi-attribute decision-making method and the objective weight assignment method based on deviation maximization. A case study with open source dataset and a performance analysis experiment are conducted to show that the proposed TaaS scheme can accurately and effectively assess the trust level of UAVs while outperforming other traditional trust assessment methods.

The adoption of lightweight container technology enables the cross-architecture deployment of Tiny Machine Learning (TinyML) models, while the implementation of container escape detectors ensures the security of both models and applications. However, a significant challenge faced by TinyML-based detectors is model aging, which leads to a substantial decline in their effectiveness as attack patterns evolve. Most existing approaches address this issue by retraining models through the labeling of new samples. However, this process can be costly and challenging to implement for updating models in resource-constrained UAVs networks. In this paper, we begin by analyzing the correlation of threat data and observe that throughout evolution, different versions of container escape attacks tend to maintain semantically identical or similar system calls. This observation prompts us to approach the model aging problem from a novel perspective: if the model can acquire knowledge of these fundamental system calls, it will be capable of effectively detecting emerging new attacks. Based on this perspective, we have developed sysE to capture system call data that remains unchanged or exhibits similarities to container escape attacks during evolution. This augmentation complements six TinyML-based detectors. Experimental results obtained from a large-scale evolving dataset demonstrate that our proposed approach effectively mitigates the aging rate of these models, reducing it from 7.3% to 21.5%. Additionally, it significantly decreases the labeling effort required from 28.06% to 65.47%.

With the advantages of lightweight and high resource utilization, cloud-native technology with containers as the core is gradually becoming the mainstream technical architecture for information infrastructure. However, malware attacks such as Doki and Symbiote threaten the container runtime's security. Malware initiates various types of runtime anomalies based on process form (e.g., modifying the process of a container, and opening the external ports). Fortunately, dynamic monitoring mechanisms have proven to be a feasible solution for verifying the trusted state of containers at runtime. Nevertheless, the current routine dynamic monitoring mechanisms for baseline data protection are still based on strong security assumptions. As a result, the existing dynamic monitoring mechanism is still not practical enough. To ensure the trustworthiness of the baseline value data and, simultaneously, to achieve the integrity verification of the monitored process, we combine blockchain and trusted computing to propose a process integrity monitoring system named IPMS. Firstly, the hardware TPM 2.0 module is applied to construct a trusted security foundation for the integrity of the process code segment due to its tamper-proof feature. Then, design a new format for storing measurement logs, easily distinguishing files with the same name in different containers from log information. Meanwhile, the baseline value data is stored on the blockchain to avoid malicious damage. Finally, trusted computing technology is used to perform fine-grained integrity measurement and remote attestation of processes in a container, detect abnormal containers in time and control them. We have implemented a prototype system and performed extensive simulation experiments to test and analyze the functionality and performance of the PIMS. Experimental results show that PIMS can accurately and efficiently detect tampered processes with only 3.57% performance loss to the container.

Numbers of applications and businesses are hosted on cloud computing platforms, and it is essential for cloud tenants to protect their data through encryption or other methods. When tenants use encryption algorithms provided by software, they are bound to face the defect that keys are not protected by hardware. Trusted computing technology can securely store the key in the hardware device. However, the hardware TPM cannot provide services for multiple VMs simultaneously. The virtual trusted computing technology virtualizes the TPM and can assign vTPM to each VM. Currently, vTPM only supports RSA, ECDSA, SHA256, and AES algorithms, et al. Relevant studies have shown that SM2/SM3/SM4 algorithms are more secure than ECDSA/SHA256/AES. In order to cope with the limitations of the cryptographic algorithms supported by vTPM, we design the vTPM-SM scheme to provide a secure and reliable SM2/SM3/SM4 algorithm application method for cloud environments. Experiments show that vTPM-SM can effectively realize the VM using Chinese commercial cryptographic algorithms through vTPM. Compared with the existing scheme, using SM2/SM3/SM4 algorithm reduces the time overhead by about 31.6%, 83.3% and 15.5%, respectively.

An efficient multi-value-proof-based remote verification scheme in the cloud environment, MURAS, is proposed to address the inefficiency of multiple component verification for virtual machines and alleviate the TPM bottleneck. We use the virtual machine introspection technique to perform semantic reconstruction outside the virtual machine, transparently capture metric logs in the virtual machine, and store virtual machine component information with the help of an unbalanced hash tree structure. Meanwhile, MURAS utilizes a multi-value proof method to complete trusted verification of multiple components based on their core authentication paths and then combines trusted proof of the virtual machine and host environment to achieve efficient verification of the integrity of the cloud platform. By verifying all evidence data at once, it can reduce frequent operations on TPM and alleviate TPM bottlenecks. By verifying all evidence data at once, it can reduce frequent operations on TPM and alleviate TPM bottlenecks. In the QEMU-KVM environment, many experiments show that with the continuous increase of the cloud platform scale, MURAS will have a more prominent efficiency of cloud platform trusted state verification.

The integration of the space–air–ground-integrated network and the Internet of Vehicles (IoV) enables the IoV to achieve full network coverage and better network performance. However, the large scale of the network and the complex cooperation mechanism make the credibility of the nodes in the network and the service delivery questioned. In this article, the hardware trusted module is used as the root of trust to build the trust chain and the trusted running environment and provide protection and trusted state attestation for services. In order to overcome the large-scale and high-concurrency performance bottlenecks in the remote verification of trusted states in the IoV, a novel batch remote approach for trusted states is proposed. The simulation results show that the proposed approach can effectively attest to the trusted state of each network node and virtual service in the IoV and enhance the trustworthiness of the network.

As an emerging virtualization technology, the Linux container provides a more lightweight, flexible, and high-performance operating-system-level virtual run-time environment. Its appearance has profoundly changed the development and deployment of multi-tier distributed applications. However, the imperfect system resource isolation features and the kernel-sharing mechanism will introduce significant security risks to the cloud platform. In this paper, we present DockerWatch, a real-time detection system for malware detection in the container-based cloud platform. DockerWatch uses a non-intrusive manner to extract executable files inside the containers, then uses the ensemble of various static features and behavior-based graphs as the analysis vector to learn the robust representations of malicious patterns. Consequently, a two-phase hybrid detection method based on deep learning is proposed to accelerate and enhance the detection performance, aiming to address the trade-off between fast and high-performance real-time detection. Extensive experiments are conducted and compared with extensive existing related methods using real-world datasets to validate the effectiveness of our system. The results show that DockerWatch achieves excellent detection performance with acceptable run-time performance overhead introduced into the platform.

Serverless computing has brought new changes to cloud computing. The decoupled serverless functions have more flexible scheduling methods and use resources efficiently with the help of autoscaling. However, it exposes more attack surfaces. If an insecure function becomes a serverless function, a significant security risk will be brought to its service. This paper analyzes the risk of asymmetric DDoS attacks faced by insecure serverless functions. These attacks can occupy a large amount of CPU or memory resources without redundant connections. They can affect the quality of service, delay response time, or even interrupt the service. Autoscaling lacks resilience to such attacks. We test the effects of these attacks in experimental environments and Alibaba Cloud's serverless application engine (SAE). In SAE, we increase the response time from 0.2 seconds to 25 seconds or crash the target function within 6 seconds. Compared with traditional DDoS attacks, asymmetric DDoS attacks are more effective for serverless applications. Finally, we design solutions to mitigate asymmetric DDoS attacks for applications with long and short response times in serverless environments.

Cloud-edge collaborative inference approach splits deep neural networks (DNNs) into two parts that run collaboratively on resource-constrained edge devices and cloud servers, aiming at minimizing inference latency and protecting data privacy. However, even if the raw input data from edge devices is not directly exposed to the cloud, state-of-the-art attacks targeting collaborative inference are still able to reconstruct the raw private data from the intermediate outputs of the exposed local models, introducing serious privacy risks. In this paper, a secure privacy inference framework for cloud-edge collaboration is proposed, termed CIS, which supports adaptively partitioning the network according to the dynamically changing network bandwidth and fully releases the computational power of edge devices. To mitigate the influence introduced by private perturbation, CIS provides a way to achieve differential privacy protection by adding refined noise to the intermediate layer feature maps offloaded to the cloud. Meanwhile, with a given total privacy budget, the budget is reasonably allocated by the size of the feature graph rank generated by different convolution filters, which makes the inference in the cloud robust to the perturbed data, thus effectively trade-off the conflicting problem between privacy and availability. Finally, we construct a real cloud-edge collaborative inference computing scenario to verify the effectiveness of inference latency and model partitioning on resource-constrained edge devices. Furthermore, the state-of-the-art cloud-edge collaborative reconstruction attack is used to evaluate the practical availability of the end-to-end privacy protection mechanism provided by CIS.

There are becoming increasingly common for Android malware with packer protection, which can effectively evade malware detection. Thus the packed identification is very required. However, current packers identification schemes cannot efficiently deal with mixed packers and fail to provide a suitable unpacking scheme. In this paper, we propose a new method called ApkClassiFy. By constructing a fingerprint feature library and classification mapping library, ApkClassiFy can accurately identify and classify Android-packed malware, effectively identifying mixed packing applications and providing a corresponding unpacking scheme. To further verify the performance of ApkClassiFy, we constructed the Android malware dataset MalApk and the packed Android malware classification dataset OmixShell. The experimental results show ApkClassiFy has higher accuracy and lower false positives in detecting packed Android malware than other packed identification schemes. Besides, ApkClassiFy can also classify packers to identify mixed packers and help analysts choose the appropriate unpacking scheme.