Software Guard Extensions Research Articles

Subgraph-level federated graph neural network for privacy-preserving recommendation with meta-learning

Graph neural networks (GNN) are widely used in recommendation systems, but traditional centralized methods raise privacy concerns. To address this, we introduce a federated framework for privacy-preserving GNN-based recommendations. This framework allows distributed training of GNN models using local user data. Each client trains a GNN using its own user–item graph and uploads gradients to a central server for aggregation. To overcome limited data, we propose expanding local graphs using Software Guard Extension (SGX) and Local Differential Privacy (LDP). SGX computes node intersections for subgraph exchange and expansion, while local differential privacy ensures privacy. Additionally, we introduce a personalized approach with Prototype Networks (PN) and Model-Agnostic Meta-Learning (MAML) to handle data heterogeneity. This enhances the encoding abilities of the federated meta-learner, enabling precise fine-tuning and quick adaptation to diverse client graph data. We leverage SGX and local differential privacy for secure parameter sharing and defense against malicious servers. Comprehensive experiments across six datasets demonstrate our method’s superiority over centralized GNN-based recommendations, while preserving user privacy.

Revolutionizing machine learning: Blockchain-based crowdsourcing for transparent and fair labeled datasets supply

With the development of 5G/6G communication networks, the industrial Internet of Things (IIoT) industry has generated a massive amount of data, presenting opportunities for advancements in the field of machine learning. The core of machine learning, labeled datasets, requires qualities such as diversity, quantity, and quality. However, the current collection of training datasets is mostly centralized, relying on crowdsourcing systems as platforms. Hence, there are four open challenges existing: (1) traditional crowdsourcing systems are mostly based on centralized platform which often suffers single point of failure, mischief attacks, DDoS attacks and are easy to be remotely hijacked; (2) the transparency of traditional crowdsourcing systems cannot be guaranteed, which results in the unfairness in assigning task or rewarding worker; (3) the quality of labeled training dataset cannot be guaranteed as the workers in traditional crowdsourcing systems are professional or non-professional; (4) the privacy of labels cannot be preserved as the platform can also learn the labeled result. In this paper, we utilize web 3.0 technology to propose a blockchain-based labeled training dataset supply system which can simultaneously supply annotation service and labeled training dataset with the challenges above overcome. Meanwhile we design a privacy-preserved truth discovery suitable for categorical data by combining it with Software Guard Extensions (SGX). Furthermore, we design a fair rewards distribution mechanism which is based on reputation system and Shapley value. The two mechanisms above can ensure the quality of labeled training dataset. Finally, to demonstrate the practicability of our design, we implement a prototype of the system deployed on Fabric test network and conduct extensive simulations. Compared to applications on public chains, the throughput of our blockchain application can reach 53 times higher.

SEDCPT: A secure and efficient Dynamic Searchable Encryption scheme with cluster padding assisted by TEE

Dynamic Searchable Symmetric Encryption (DSSE), which enables users to search and update encrypted data on an untrusted server without decryption, is a proven method when dealing with availability issues for outsourced data. However, the existing DSSE schemes suffer from forward and backward privacy problems. Although forward and backward privacy DSSE schemes can prevent these attacks, they still suffer from other challenges, such as count attacks, high communication overhead, and low computing efficiency. To solve the above problems simultaneously, we propose a secure and efficient dynamic searchable encryption scheme, which integrates a clustering algorithm, padding strategy, and trusted execution environments (TEE). The purpose of the scheme is to prevent count attacks while ensuring forward and backward privacy security. Our scheme also reduces the computing overhead and storage cost of the client by using TEE (e.g. Intel Software Guard Extension, Intel SGX) while maximizing the protection of client privacy. Furthermore, the scheme provides a secure hardware isolation environment for the cluster padding and search/update process to prevent malicious attacks from external software or super administrators. Finally, we provide corresponding security proofs and experimental evaluation which demonstrate both the security and efficiency of our scheme, respectively.

PPPCT: Privacy-Preserving framework for Parallel Clustering Transcriptomics data

Single-cell transcriptomics data provides crucial insights into patients’ health, yet poses significant privacy concerns. Genomic data privacy attacks can have deep implications, encompassing not only the patients’ health information but also extending widely to compromise their families’. Moreover, the permanence of leaked data exacerbates the challenges, making retraction an impossibility. While extensive efforts have been directed towards clustering single-cell transcriptomics data, addressing critical challenges, especially in the realm of privacy, remains pivotal. This paper introduces an efficient, fast, privacy-preserving approach for clustering single-cell RNA-sequencing (scRNA-seq) datasets. The key contributions include ensuring data privacy, achieving high-quality clustering, accommodating the high dimensionality inherent in the datasets, and maintaining reasonable computation time for big-scale datasets. Our proposed approach utilizes the map-reduce scheme to parallelize clustering, addressing intensive calculation challenges. Intel Software Guard eXtension (SGX) processors are used to ensure the security of sensitive code and data during processing. Additionally, the approach incorporates a logarithm transformation as a preprocessing step, employs non-negative matrix factorization for dimensionality reduction, and utilizes parallel k-means for clustering. The approach fully leverages the computing capabilities of all processing resources within a secure private cloud environment. Experimental results demonstrate the efficacy of our approach in preserving patient privacy while surpassing state-of-the-art methods in both clustering quality and computation time. Our method consistently achieves a minimum of 7% higher Adjusted Rand Index (ARI) than existing approaches, contingent on dataset size. Additionally, due to parallel computations and dimensionality reduction, our approach exhibits efficiency, converging to very good results in less than 10 seconds for a scRNA-seq dataset with 5000 genes and 6000 cells when prioritizing privacy and under two seconds without privacy considerations.Availability and implementationCode and datasets availability: https://github.com/University-of-Windsor/PPPCT.

A Secure and Efficient Dynamic Analysis Scheme for Genome Data within SGX-Assisted Servers

With the rapid development of the Internet of Things (IoT), more and more user devices access the network and generate large amounts of genome data. These genome data possess significant medical value when researched. However, traditional genome analysis confronts security and efficiency challenges, including access pattern leakage, low efficiency, and single analysis methods. Thus, we propose a secure and efficient dynamic analysis scheme for genome data within a Software Guard Extension (SGX)-assisted server, called SEDASGX. Our approach involves designing a secure analysis framework based on SGXs and implementing various analysis methods within the enclave. The access pattern of genome data is always obfuscated during the analysis and update process, ensuring privacy and security. Furthermore, our scheme not only achieves higher analysis efficiency but also enables dynamic updating of genome data. Our results indicate that the SEDASGX analysis method is nearly 2.5 times more efficient than non-SGX methods, significantly enhancing the analysis speed of large-scale genome data.

GUARDIAN: A Hardware-Assisted Distributed Framework to Enhance Deep Learning Security

The ubiquity of artificial intelligence (AI) has led to its extensive research and application in various fields, such as computer vision, natural language processing, and medical image analysis. However, responsible AI faces severe security challenges, including the leakage of pretrained models and valuable training data. The existing solutions adopt new algorithm designs (such as federated learning) or cryptography (such as homomorphic encryption) to prevent possible security vulnerabilities. We observe that hardware-assisted trusted execution environments (TEEs) can further improve machine learning responsibility. Intel Software Guard Extension (SGX) is a popular, trusted execution hardware that enables users’ programs to run in an untrusted execution environment, such as a malicious operating system, but ensures the confidentiality and integrity of data. Therefore, we have designed, a hardware-assisted secure machine learning training framework that protects data security during the training process. We have analyzed the typical characteristics of machine learning applications and characterized through extensive experiments. Our findings demonstrate that introducing security guarantees causes performance degradation, which provides a feasible optimization direction in the near future.

A trust-aware openflow switching framework for software defined networks (SDN)

Software Defined Networks (SDN) and Network Function Virtualisation (NFV) are prime driving technologies behind 5G and Beyond 5G (B5G) communications. The network control intelligence segregation in the SDN infrastructure enables dynamic network features (such as dynamic end-to-end management of security and quality of service (QoS)) offering significantly improved network performance. Even if one assumes that the centralised SDN controller can be security hardened and hence can be trusted, a fundamental challenge in such networks is that the data plane and switching devices are susceptible to cyberattacks. A malicious adversary can compromise them during run-time making them unreliable for secure and trusted communications. Furthermore, the controller communicating with OpenFlow switching devices is unable to accurately assess the state of the switching devices, which serves as the communication base for NFVs in 5G networks. Vulnerable switching devices can put the whole 5G network infrastructure at risk. Hence, there is a clear need for the controller and the management layer to determine the trustworthiness of the switching devices at run-time. The current trend is for many such devices to deploy trusted computing functionality such as Trusted Platform Module (TPM) or Software Guard Extension (SGx) to achieve local as well as remote attestation. In this paper, we present a dynamic trust management framework for evaluating the trustworthiness of the OpenFlow switching devices deployed in the SDN based networks. We formulate device properties that need to be assessed to determine the trust status of the device. We develop a trust enhanced security architecture which can be used to evaluate the trustworthiness of devices and determine their deployment in the provision of network services. The proposed framework uses subjective logic based techniques to derive trust levels of the switching devices at run-time, which are then used by the architecture to make trust enhanced decisions on the provision of network services. A prototype implementation of the proposed architecture is described, which demonstrates how the trustworthiness of the OpenFlow devices are assessed at run-time. The paper concludes with the performance and security analysis of the implemented trust enhanced architecture services.

POMF: A Privacy-preserved On-chain Matching Framework

With the growth of the Internet, an increasing number of online matching platforms have emerged. However, current online matching platforms need to address three open challenges to improve user experience: (1) transparency and inherent issues with centralized platforms; (2) privacy concerns of users’ sensitive information; and (3) high service fees for matching services. In this paper, we propose a Privacy-preserved On-chain Matching Framework (POMF) that is suitable for a broad range of matching scenarios to overcome the challenges above simultaneously. In order to address the first challenge, POMF is constructed via the decentralized blockchain, based on which smart contracts are utilized to execute matching services automatically and publicly. To address the second challenge, we combine Order-Preserved Encryption (OPE) with Software Guard Extensions (SGX) to design a privacy-preserved on-chain matching mechanism that can enable information matching among different users in the encrypted domain, while revealing only order information and maintaining confidentiality. To address the third challenge, we optimize the OPE algorithm to reduce its computing and communication overhead, which further reduces the matching service fee. Besides, we ensure the fairness of POMF by designing a reasonable price mechanism that prices the contact information based on the matching degree between the involved matched users. Finally, we prove the availability of POMF via an comprehensive analysis and demonstrate the practicality of POMF by implementing a prototype and deploying it on a Fabric test network with extensive simulations.

Enhancing the Security and Privacy in the IoT Supply Chain Using Blockchain and Federated Learning with Trusted Execution Environment

Federated learning has emerged as a promising technique for the Internet of Things (IoT) in various domains, including supply chain management. It enables IoT devices to collaboratively learn without exposing their raw data, ensuring data privacy. However, federated learning faces the threats of local data tampering and upload process attacks. This paper proposes an innovative framework that leverages Trusted Execution Environment (TEE) and blockchain technology to address the data security and privacy challenges in federated learning for IoT supply chain management. Our framework achieves the security of local data computation and the tampering resistance of data update uploads using TEE and the blockchain. We adopt Intel Software Guard Extensions (SGXs) as the specific implementation of TEE, which can guarantee the secure execution of local models on SGX-enabled processors. We also use consortium blockchain technology to build a verification network and consensus mechanism, ensuring the security and tamper resistance of the data upload and aggregation process. Finally, each cluster can obtain the aggregated parameters from the blockchain. To evaluate the performance of our proposed framework, we conducted several experiments with different numbers of participants and different datasets and validated the effectiveness of our scheme. We tested the final global model obtained from federated training on a test dataset and found that increasing both the number of iterations and the number of participants improves its accuracy. For instance, it reaches 94% accuracy with one participant and five iterations and 98.5% accuracy with ten participants and thirty iterations.

Nereus: Anonymous and Secure Ride-Hailing Service Based on Private Smart Contracts

Security and privacy issues have become a major hindrance to the broad adoption of Ride-Hailing Services (RHSs). In this paper, we introduce a new collusion attack initiated by the Ride-Hailing Service Provider (RHSP) and a driver that could easily link the real riders and their anonymous requests (credentials). Besides this attack, existing work requires heavy computations to execute user matching, and it is challenging for riders to verify matching results. Meanwhile, a malicious driver may cancel an assigned ride order due to its short distance. To address these issues, we present a RHS system named Nereus to support collusion resistance, efficiency, verifiability, and accountability. First, we integrate a smart contract into a Software Guard Extensions (SGX) enclave to establish a <i>private smart contract</i> for collusion resistance. We use a Bloom filter to achieve efficient matching. Second, we leverage privacy-preserving range query and Merkle proofs to make matching results verifiable. Meanwhile, we adopt short group signatures to provide anonymous authentication and deposit commitments to hold the runaway driver accountable. We formally state and prove the security and privacy of Nereus. We build a prototype based on Ethereum and SGX to conduct extensive performance analysis in regard to gas costs, computational costs, and communication overhead. Experimental results show that Nereus significantly improves over existing schemes in terms of computational costs.

Securing TEEs With Verifiable Execution Contracts

Recent works have demonstrated that trusted execution environments, such as Intel Software Guard Extensions, are vulnerable to various attacks from the privileged software, including side-channel attacks. Existing solutions, such as T-SGX, D&#x00E9;j&#x00E0; Vu, Cloak and Varys, detect side-channel attacks at runtime. But they are limited by design, because false detection is unavoidable in these detection methods and therefore any security policy developed atop these mechanisms has to tolerate some malicious operations to achieve practical false positive detection rates. In this paper, we propose the concept of verifiable execution contracts, which request the privileged software to provide a benign execution environment for enclaves within which launching attacks becomes very difficult, if not impossible. Since the privileged software is untrusted, we design methods for verifying that the execution contracts are observed. With the proposed verifiable execution contracts, we analyzed how existing attacks could be mitigated.

Securing Federated Learning Based on Blockchain Technology

A blockchain-based federated learning approach with secure aggregation in a trusted execution environment for the Internet of Things (IoT). The proposed approach aims to address the privacy and security concerns associated with federated learning in IoT environments. The approach involves using a blockchain to store the learning model and to maintain a distributed ledger of transactions. The learning model is trained on local IoT devices using federated learning techniques, with each device contributing its local data. The aggregation of the model updates is performed securely within a trusted execution environment, using homomorphism encryption and secret sharing techniques. The proposed approach offers several advantages over traditional federated learning approaches, including improved privacy and security, increased scalability, and enhanced trustworthiness. It also enables the creation of a decentralized and democratic learning environment, where each device has an equal say in the learning process. The approach is evaluated using a real-world dataset, and the results demonstrate its effectiveness in terms of accuracy and privacy preservation. The paper concludes that the proposed approach has the potential to enable secure and scalable federated learning in IoT environments, with applications in healthcare, smart cities, and other domains. This paper offers a blockchain-based federated learning (FL) framework with an Intel Software Guard Extension (SGX)-based trusted execution environment (TEE) for safely aggregating local models in the Industrial Internet of Things (IoT) Local models in FL can be modified with by attackers. As a result, a global model derived from manipulated local models may be incorrect. As a result, the proposed system makes use of a blockchain network to secure model aggregation. Each blockchain node contains an SGX-enabled CPU that secures the FL-based aggregating processes required to construct a global model. Blockchain nodes may validate the aggregated model's validity, perform a blockchain consensus method to secure the model's integrity, and add it to the distributed ledger for tamper-proof storage. . Before utilising the aggregated model, each cluster can acquire it from the blockchain and validate its fidelity. To assess the performance of the proposed system, we ran many experiments using various CNN models and datasets

Impact of Emerging Hardware on Security and Privacy

The articles in this special issue focus on ongoing research efforts in the development, use, and evaluation of emerging hardware features and techniques to improve system security. We have seen the emergence of new hardware features to improve software security by limiting memory access within an address space, such as Intel’s memory protection keys (MPKs) and extended page table (EPT) switching, among others. Researchers have also proposed hardware-assisted roots of trust using trusted execution environments (TEEs), such as Intel’s software guard extensions (SGXs), so some questions are what the utility is of such techniques and what limitations they still face. The papers in this special issue provide guidance in these areas, which can be helpful in examining future research directions and future applications of such techniques.

Blockchain-Based Federated Learning With Secure Aggregation in Trusted Execution Environment for Internet-of-Things

This paper proposes a blockchain-based Federated Learning (FL) framework with Intel Software Guard Extension (SGX)-based Trusted Execution Environment (TEE) to securely aggregate local models in Industrial Internet-of-Things (IIoTs). In FL, local models can be tampered with by attackers. Hence, a global model generated from the tampered local models can be erroneous. Therefore, the proposed framework leverages a blockchain network for secure model aggregation. Each blockchain node hosts an SGX-enabled processor that securely performs the FL-based aggregation tasks to generate a global model. Blockchain nodes can verify the authenticity of the aggregated model, run a blockchain consensus mechanism to ensure the integrity of the model, and add it to the distributed ledger for tamper-proof storage. Each cluster can obtain the aggregated model from the blockchain and verify its integrity before using it. We conducted several experiments with different CNN models and datasets to evaluate the performance of the proposed framework.

Trust Beyond Border: Lightweight, Verifiable User Isolation for Protecting In-Enclave Services.

Due to the absence of in-enclave isolation, today's trusted execution environment (TEE), specifically Intel's Software Guard Extensions (SGX), does not have the capability to securely run different users' tasks within a single enclave, which is required for supporting real-world services, such as an in-enclave machine learning model that classifies the data from various sources, or a microservice (e.g., data search) that performs a very small task (within sub-seconds) for a user and therefore cannot afford the resources and the delay for creating a separate enclave for each user. To address this challenge, we developed Liveries, a technique that enables lightweight, verifiable in-enclave user isolation for protecting time-sharing services. Our approach restricts an in-enclave thread's privilege when configuring an enclave, and further performs integrity check and sanitization on critical enclave data upon user switches. For this purpose, we developed a novel technique that ensures the protection of sensitive user data (e.g., session keys) even in the presence of the adversary who may have compromised the enclave. Our study shows that the new technique is lightweight (1% overhead) and verifiable (about 3200 lines of code), making a step towards assured protection of real-world in-enclave services.

Efficient and Secure Deep Learning Inference in Trusted Processor Enabled Edge Clouds

Edge intelligence has emerged as a prevalent enabling technology to support various intelligent applications. Along with the prosperity, it also raises great concern on the security and privacy since the edge servers are usually shared and untrusted. The security-sensitive code (i.e., the pre-trained model) and data may be easily stolen by malicious tenants, and even untrusted infrastructure providers. To this end, Software Guard Extensions (SGX) is proposed to provide an isolated Trust Execution Environment (TEE) for security and privacy guarantee. However, we find that running tasks in SGX suffer certain performance degradation due to the limited Enclave Page Cache (EPC) size. This further leads to frequent page swapping operations and the high enclave call overhead, which are also influenced by the task (i.e., DNN layer) dispatching and scheduling. To this end, in this paper, we design <b>Lasagna</b> , as an SGX based secure DNN inference acceleration framework, which explores the layered-structure of DNN models to well balance the usage of the scarce EPC resources and the computation resources. Lasagna mainly consists of a global task balancer and a local task scheduler, responding for task dispatching across distributed edge servers and task scheduling in local server, respectively. We evaluate Lasagna over different well-known DNN models, and the results show that Lasagna effectively speeds up the inference performance by <inline-formula><tex-math notation="LaTeX">$1.11\times -1.51\times$</tex-math></inline-formula> .

A secure double spectrum auction scheme

With the arrival of the 5G era, wireless communication technologies and services are rapidly exhausting the limited spectrum resources. Spectrum auctions came into being, which can effectively utilize spectrum resources. Because of the complexity of the electronic spectrum auction network environment, the security of spectrum auction can not be guaranteed. Most scholars focus on researching the security of the single-sided auctions, while ignoring the practical scenario of a secure double spectrum auction where participants are composed of multiple sellers and buyers. Researchers begin to design the secure double spectrum auction mechanisms, in which two semi-honest agents are introduced to finish the spectrum auction rules. But these two agents may collude with each other or be bribed by buyers and sellers, which may create security risks, therefore, a secure double spectrum auction is proposed in this paper. Unlike traditional secure double spectrum auctions, the spectrum auction server with Software Guard Extensions (SGX) component is used in this paper, which is an Ethereum blockchain platform that performs spectrum auctions. A secure double spectrum protocol is also designed, using SGX technology and cryptographic tools such as Paillier cryptosystem, stealth address technology and one-time ring signatures to well protect the private information of spectrum auctions. In addition, the smart contracts provided by the Ethereum blockchain platform are executed to assist offline verification, and to verify important spectrum auction information to ensure the fairness and impartiality of spectrum auctions. Finally, security analysis and performance evaluation of our protocol are discussed.

GDPR-Aware Revocable P2P File-Sharing System Over Consortium Blockchain

With the rise of blockchain technology, the peer-to-peer (P2P) network system has once again caught people's attention to equipping a blockchain with a big storage capacity. In the traditional P2P file-sharing network systems, such as InterPlanetary File System (IPFS), data stored in the other nodes cannot be revoked by the owner and can only be removed by other nodes themselves. To comply with the criteria of the European Union's General Data Protection Regulation, it is important to ensure that personal data can be completely removed by their owners. To improve the privacy and security of the P2P file-sharing system, we propose a revocable and monitorable P2P file-sharing system over a consortium blockchain to achieve revocation of files in the decentralized environment. By using a trusted execution environment, such as Intel Software Guard Extensions (SGX), the proposed scheme can verify the integrity of the executables of the P2P file-sharing system and generate a file authentication code for each IPFS node to make sure that the system is synchronized correctly. This scheme elaborately integrates the autonomous smart contracts and Intel SGX hardware to obtain the monitorable merit. The experimental results suggest that enhancing the security and privacy take modest computing costs into consideration. To the best of our knowledge, this scheme is the first attempt to achieve the P2P file-sharing system with securely revocable functions.

Integrity of virtual testing for crash protection

The interest in virtual testing is globally rapidly increasing because of several advantages compared to physical tests in laboratories. In the area of passive car safety, finite element simulations can be used to get further insights, use more biofidelic human models and make the overall assessment more robust by incorporating more variety in the virtual testing load cases. For a successful implementation of virtual testing in regulations or consumer information, the integrity of the procedure has to be ensured. As car simulation models used within the virtual testing are usually not shared with the evaluation institutions due to intellectual property (IP) issues, this is a challenging task. Stringent validation and certification procedures are needed and it has to be ensured that the models used in these steps are the same as the ones used for the virtual testing. In this paper, we developed a secure procedure for model version control. Through analysis of possible threats for both sides, car manufacturer and evaluation institution, we defined requirements, which the new procedure should satisfy. These requirements state that the integrity and authenticity of all shared documents should be protected, as well as the confidentiality of the simulation model. By considering all prerequisites, we developed an architecture for a new procedure. This architecture uses cryptographic algorithms such as hash functions and digital signatures to ensure integrity and authenticity, as well as secure computation mechanisms such as Intel Software Guard Extensions (SGX). In our proof-of-concept implementation, we demonstrated how a secure wrapper around LS-DYNA can produce a signed report to authenticate the input model files based on a hash tree and link them to the simulation results. The evaluation institution can use a matching verification tool to verify that the models were not manipulated compared to other simulation runs or the qualification process. The developed procedure can be used for trustworthy implementation of virtual testing into consumer information or regulation for the assessment of car safety with strengthened integrity. Further research is needed to develop comparable procedures for other simulation software packages or ideally integrate it directly into the simulation software.

FaultMorse: An automated controlled-channel attack via longest recurring sequence

With the rise of the concept of Trusted Execution Environments (TEEs), such as Intel Software Guard Extensions (SGX), researchers are prompted to constantly verify its effectiveness. Controlled-channel attacks are proposed to construct side channels against the shielding systems by intentionally provoking page faults. So far, various powerful and noise-free controlled-channel attacks have been introduced. However, there are some challenges encountered in the actual practice of these attacks, e.g., extensive manual effort is always required to analyze the target binary and identify conditional control-flow patterns.In this paper, we present FaultMorse, an automated controlled-channel attack. We adopt a global perspective to analyze the page fault sequence and find a specific recurring pattern that corresponds to some specific instructions in the program. Most of the secret bits can be automatically deduced by analyzing the locations of the recurring pattern in the page fault sequence. Compared to previous works, FaultMorse can reduce the complexity of analysis. We propose a method to control page fault counts to improve the attack performance. We implement our FaultMorse attack on a physical machine and evaluate its effectiveness, universality, and page-fault rate. The experimental results show that for some known vulnerable algorithms, FaultMorse can automatically deduce more than 99% of the secret bits.