Aggregation Scheme Research Articles

RFedFW: Secure and trustable aggregation scheme for Byzantine-robust federated learning in Internet of Things

Federated learning is a promising approach in the Internet of Things (IoT) that enables collaborative and distributed machine learning among massive IoT devices without sharing private data, thereby constructing smart IoT applications. However, traditional federated learning approaches are unable to monitor the local training process of devices. Some malicious devices can exploit the vulnerability to conduct Byzantine attacks, which may potentially lead to the failure or compromise of shared global model. In this paper, we propose a new Byzantine-robust federated learning framework called rFedFW, which aims to achieve secure and trustable federated learning in the IoT. Specifically, we propose a dual filtering mechanism to identify and discard malicious gradients. Furthermore, we design an adaptive weight adjustment scheme that dynamically reduces the aggregated weight of potentially malicious gradients, ultimately achieving robust model aggregation. Additionally, we propose a dynamic clipping method to reduce the magnitude of various gradients, and we incorporate an additive model aggregation scheme with momentum to smooth the effects of local gradients and achieve efficient model aggregation. Extensive experimental results on various datasets demonstrate the effectiveness and robustness of rFedFW.

Privacy-preserving and Byzantine-robust Federated Learning Framework using Permissioned Blockchain

Data is readily available with the growing number of smart and IoT devices. However, application-specific data is available in small chunks and distributed across demographics. Also, sharing data online brings serious concerns and poses various security and privacy threats. To solve these issues, federated learning (FL) has emerged as a promising secure and collaborative learning solution. FL brings the machine learning model to the data owners, trains locally, and then sends the trained model to the central curator for final aggregation. However, FL is prone to poisoning and inference attacks in the presence of malicious participants and curious servers. Different Byzantine-robust aggregation schemes exist to mitigate poisoning attacks, but they require raw access to the model updates. Thus, it exposes the submitted updates to inference attacks. This work proposes a Byzantine-Robust and Inference-Resistant Federated Learning Framework using Permissioned Blockchain, called PrivateFL. PrivateFL replaces the central curator with the Hyperledger Fabric network. Further, we propose VPSA (Vertically Partitioned Secure Aggregation), tailored to PrivateFL framework, which performs robust and secure aggregation. Theoretical analysis proves that VPSA resists inference attacks, even if n−1 peers are compromised. A secure prediction mechanism to securely query a global model is also proposed for PrivateFL framework. Experimental evaluation shows that PrivateFL performs better than the traditional (centralized) learning systems, while being resistant to poisoning and inference attacks.

DRL-Based Secure Aggregation and Resource Orchestration in MEC-Enabled Hierarchical Federated Learning

Federated learning (FL) provides a new paradigm for protecting data privacy by enabling model training at devices and model aggregation at servers. However, data information may be leaked to honest-but-curious aggregation servers by updated model parameters. The existing secure methods do not fully exploit the potentiality of data characteristics in enhancing security, which makes it impossible to optimize limited system resources overall to achieve secure, fair and efficient FL systems. In this paper, a DRL-based joint secure aggregation and resource orchestration scheme is proposed to guarantee security and fairness, and improve efficiency for hierarchical FL assisted by untrusted mobile-edge computing (MEC) servers. We formulate a joint optimization problem of data size, payment and resource orchestration, to maximize the long-term social welfare subject to secure aggregation and limited resources. Since the formulated problem is a complex mixed integer dynamic optimization problem with NP-hardness, where multiple mixed integer optimization variables are highly coupled in time-varying constraints and objective function, it is difficult to obtain its optimal solution via traditional optimization methods. Thus, we propose a hierarchical reward function-based DRL algorithm (MATD3) to guide the agents to approach the optimal policy of secure aggregation and resource orchestration. Simulation results show that the proposed algorithm MATD3 can achieve superior performance over comparison algorithms and the MEC-enabled HFL framework outperforms two-layer FL frameworks.

Cross-Efficiency aggregation based on the denominator rule

In this paper we propose an alternative cross-efficiency aggregation scheme that is based on the theory underlying the aggregation of self-appraisal efficiency scores. For this purpose, we apply the denominator rule to aggregate the cross-efficiency scores obtained from the multiplier form of the DEA model. This results in a share-weighted average cross-efficiency that takes explicitly into account the relative importance of each element of the cross efficiency matrix by means of either the opportunity cost of resources used or the value of outputs produced, depending upon the orientation chosen to measure efficiency. It turns out that the proposed share-weighting average cross-efficiency uses the simple arithmetic average of the estimated input and output weights from the self-appraisal form of the DEA model to compute the ultimate cross-efficiency. As this is a set of common (across decision-making units) input and output weights, it allows for complete ranking and comparison of all (efficient and inefficient) decision-making units.

Privacy and integrity-preserving data aggregation scheme for wireless sensor networks digital twins

The security technology of digital twin is an important guarantee to ensure the security of digital twin operation, which mainly includes network security technology, data security technology and privacy protection technology. In wireless sensor networks, data aggregation technologies are known as a suitable solution to reduce energy consumption. In addition, due to wireless communications, wireless sensor networks are subject to many attacks. Therefore, it is very important to provide data security in the data aggregation process. In this paper, in order to protect data privacy and verify data integrity, moreover, balance the energy consumption and security during the data aggregation, we present a privacy and integrity–preserving data aggregation scheme for wireless sensor networks based on digital twins technology and homomorphic fingerprinting (HFPIDA). The HFPIDA adopts privacy function to protect data privacy and adopts homomorphic fingerprinting technology to verify the aggregation data integrity. Security analysis shows that the HFPIDA can effectively preserve data privacy and verify data integrity. Simulation results show that the HFPIDA requires less communication and energy overheads, and can achieve higher aggregation accuracy.

Generalized theory for measuring efficiency of individuals and groups

We present a cohesive generalized framework for an aggregation of the Nerlovian profit indicators and of the directional distance functions, frequently used in productivity and efficiency analysis in operations research and econometrics (e.g., via data envelopment analysis or stochastic frontier analysis). Our theoretical framework allows for greater flexibility than previous approaches, and embraces many other approaches as special cases. In the proposed aggregation scheme, the aggregation weights are mathematically derived from assumptions made about the optimization behavior and about the chosen directions of measurement. We also discuss various interesting special cases of popular directions, including the case of Debreu-Farrell-type efficiency.

A Novel Blockchain-Assisted Aggregation Scheme for Federated Learning in IoT Networks

With the wide range of Internet of things (IoT) applications, Federated Learning (FL) is commonly adopted to protect the privacy of IoT data. FL enables privacy-preserving model training while keeping the data locally available. To alleviate the additional load caused by FL, an improved hierarchical aggregation framework is presented in this paper to decentralize the model aggregation tasks based on end-device clusters. However, when applying FL to IoT networks, how to keep high efficiency and reliability remains open challenges due to a large number and vulnerability of IoT end-devices. In this paper, we propose a blockchain-assisted aggregation scheme for FL in IoT networks, where the aggregation node selection is applied for efficiency improvement as well as blockchain for performance verification. During model aggregation, a selection strategy is obtained by the Deep Deterministic Policy Gradient (DDPG) algorithm and aims to select the optimal subset of IoT end-devices based on multiple metrics. Furthermore, a new performance verification based on the characteristics of blockchain is applied to achieve mutual verification among a number of untrustworthy nodes with the optimal stopping theory, which provides reliable model performance proofs. Simulation results show that the proposed scheme can maintain FL efficiency and reduce the system latency while protecting data privacy.

BCSoM: Blockchain-based certificateless aggregate signcryption scheme for Internet of Medical Things

The integration of fog computing and blockchain in the Internet of Medical Things (IoMT) domain has wholly transformed the healthcare industry and e-health services. In IoMT, the patient’s personal health data is shared on an open channel that makes the IoMT system an easy target for attackers. Therefore, confidentiality and authentication are the key security requirements for an IoMT system. Although few works have been proposed to provide secure communication in conventional healthcare infrastructures, limited work has been done to achieve data confidentiality and authentication in blockchain-based IoMT under fog environment. Therefore, this work proposes a blockchain-assisted certificateless aggregate signcryption called BCSoM scheme that achieves data confidentiality and device/patient authentication. In the proposed work, first, IoMT devices generate a signcrypted text and transmit it to an aggregator that generates an aggregated signcrypted text and sends it to a receiver fog server. The receiver fog server verifies the signcrypted text through the blockchain and also performs unsigncryption to retrieve the original message. The proposed scheme is proven secure under the Discrete Logarithm (DL) and Computational Diffe–Hellman (CDH) assumptions. Finally, a thorough performance analysis using the Hyperledger Fabric platform and cryptographic libraries shows that the proposed scheme is computationally more efficient when compared to existing works.

Two level data centric aggregation scheme for wireless sensor networks

Two level data centric aggregation scheme for wireless sensor networks

ComAvg: Robust decentralized federated learning with random committees

Federated learning (FL) has been widely used in IoT applications. However, FL is vulnerable to various attacks in its each phase. Existing defense in federated learning mainly focus on the centralized setting. And centralized parameter-server settings require a trusted third party to collect and distribute model parameters. However, the requirement of a trusted third party cannot always be satisfied in many cases. Meanwhile, the centralized settings suffer from the inherent vulnerability of single-point-of-failure (SPOF), in which the whole system cease to function once the parameter server is broken. Therefore, decentralized federated learning has gain great attention recently.Existing conventional defense strategies are mostly designed for the centralized parameter-server architecture. The problem is that these conventional defense strategies cannot cope with new challenges occurred in highly decentralized settings of FL. Firstly, in a trustless setting, malicious participants can cause breakdown to the whole system on the communication level by disrupting model exchanges. Secondly, current defensive methods cannot effectively identify and rule out malicious participants. In either case, a harmful bias hurts the performance even if malicious participants do not perform model-level attacks. Therefore, defensive strategies for the decentralized-manner FL are in urgent need. To this end, we propose a committee-based FL system, named ComAvg, under a trustless setting. ComAvg provides a general coordination scheme for robust aggregation of distributed learning. With reliability assessment scheme to expel abnormal participants and fortified classic model exchange methods, the conventional centralized methods of FL can be easily modified into decentralized versions to cope with the two challenges aforementioned. Finally, we implement a prototype of ComAvg and perform various groups of evaluations on its robustness. The prototype-based evaluation results and theoretical analysis show that the proposed ComAvg is effective against model attacks such as sign-flipping and communication-level isolating attacks.

Multi-View Feature Aggregation for Predicting Microbe-Disease Association.

Microbes play a crucial role in human health and disease. Figuring out the relationship between microbes and diseases leads to significant potential applications in disease treatments. It is an urgent need to devise robust and effective computational methods for identifying disease-related microbes. This work proposes a Multi-View Feature Aggregation (MVFA) scheme that integrates the linear and nonlinear features to identify disease-related microbes. We introduce a non-negative matrix tri-factorization (NMTF) model to extract linear features for diseases and microbes. Then we learn another type of linear feature by utilizing a bi-random walk model. The nonlinear feature is obtained by inputting the two kinds of linear features into a capsule neural network. These three types of features describe the associations between diseases and microbes from different views. Finally, considering the complementary of these features, we leverage a logistic regression model to combine the NMTF model predictions, bi-random walk model predictions, and the capsule neural network predictions to obtain the final microbe-disease pair scores. We apply our method to predict human microbe-disease associations on two datasets. Experimental results show that our multi-view model outperforms the state-of-the-art models in recovering missing microbe-disease associations and predicting associations for new microbes. The ablation study shows that aggregating multi-view linear and nonlinear features can improve the prediction performance. Case studies on two diseases, i.e. Type 1 diabetes and Liver cirrhosis, further validate our method effectiveness.

Fault-Tolerant Aggregate Signature Schemes against Bandwidth Consumption Attack

A fault-tolerant aggregate signature (FT-AS) scheme is a variant of an aggregate signature scheme with the additional functionality to trace signers that create invalid signatures in case an aggregate signature is invalid. Several FT-AS schemes have been proposed so far, and some of them trace such rogue signers in multi-rounds, i.e., the setting where the signers repeatedly send their individual signatures. However, it has been overlooked that there exists a potential attack on the efficiency of bandwidth consumption in a multi-round FT-AS scheme. Since one of the merits of aggregate signature schemes is the efficiency of bandwidth consumption, such an attack might be critical for multi-round FT-AS schemes. In this paper, we propose a new multi-round FT-AS scheme that is tolerant of such an attack. We implement our scheme and experimentally show that it is more efficient than the existing multi-round FT-AS scheme if rogue signers randomly create invalid signatures with low probability, which for example captures spontaneous failures of devices in IoT systems.

An efficient and privacy-preserving blockchain-based secure data aggregation in smart grids

Smart Grids (SGs) present a number of advantages over traditional grid like reduce energy cost, reduce energy wastage, and increase reliability and transparency. However, it also introduces a number of security and privacy issues not foreseen before. These are very serious issues from consumer’s perspective who do not want any malicious entity to infer any personal information from the consumption data. Data aggregation plays a significant role in protecting user’s consumption data. SGs deploy a single entity, called an aggregator, to collect and aggregate end users’ encrypted consumption data. While a number of secure data aggregation schemes have been proposed, many existing schemes suffer from a single point of failure in the aggregation process. Recently, some blockchain-based data aggregation schemes have been proposed to overcome this problem. While overcoming the failure issues, these schemes do not provide the necessary security and privacy requirements of smart grids. Furthermore, these schemes suffer from high computation and communication cost due to the use of RSA-based signatures. In order to solve these issues, this paper proposes a decentralized secure data aggregation scheme using blockchain which preserves privacy, integrity, authentication, and confidentiality of individual consumption data. Experimental results show that the proposed scheme effectively protects end user consumption data.

A Multidimensional Data Aggregation Scheme of Smart Home in Microgrid With Fault Tolerance and Billing for Demand Response

A Multidimensional Data Aggregation Scheme of Smart Home in Microgrid With Fault Tolerance and Billing for Demand Response

A Privacy-Preserving Data Aggregation Scheme Based on Chinese Remainder Theorem in Mobile Crowdsensing System

Mobile crowdsensing provides a large-scale reliable data, since sensing nodes support wide distribution, flexible mobility, and opportunistic connectivity. The generated data often contains the sensing node's sensitive information. Existing schemes dedicated to protecting the privacy of perception data, but these schemes cannot balance the computational and communication overheads well. Therefore, we propose a privacy-preserving data aggregation scheme based on the Chinese remainder theorem. Using blinding factor and Paillier homomorphic encryption technology, which not only ensures the privacy of perceived data but also improves the robustness of the system. Specially, the introduction of secure multicast communication technology based on the Chinese remainder theorem protects task privacy and ensures only designated sensing nodes can obtain the task. In addition, we design an efficient signature scheme to ensure data integrity. Detailed security analysis shows that our scheme is existentially unforgeable against adaptively chosen message attack. Extensive experiments and performance analysis show that our scheme is efficient and has a low communication overhead.

An Improved Federated Learning-Assisted Data Aggregation Scheme for Smart Grids

In the context of rapid advancements in artificial intelligence (AI) technology, new technologies, such as federated learning and edge computing, have been widely applied in the power Internet of Things (PIoT). When compared to the traditional centralized training approach, conventional federated learning (FL) significantly enhances privacy protection. Nonetheless, the approach poses privacy concerns, such as inferring other users’ training data through the global model or user-transferred parameters. In light of these challenges, this research paper introduces a novel privacy-preserving data aggregation scheme for the smart grid, bolstered by an improved FL technique. The secure multi-party computation (SMC) and differential privacy (DP) are skillfully combined with FL to combat inference attacks during both the learning process and output inference stages, thus furnishing robust privacy assurances. Through this approach, a trusted third party can securely acquire model parameters from power data holders and securely update the global model in an aggregated way. Moreover, the proposed secure aggregation scheme, as demonstrated through security analysis, achieves secure and reliable data aggregation in the electric PIoT environment. Finally, the experimental analysis shows that the proposed scheme effectively performs federated learning tasks, achieving good model accuracy and shorter execution times.

An elliptic curve cryptography based certificate-less signature aggregation scheme for efficient authentication in vehicular ad hoc networks

An elliptic curve cryptography based certificate-less signature aggregation scheme for efficient authentication in vehicular ad hoc networks

Federated causal inference in heterogeneous observational data.

We are interested in estimating the effect of a treatment applied to individuals at multiple sites, where data is stored locally for each site. Due to privacy constraints, individual-level data cannot be shared across sites; the sites may also have heterogeneous populations and treatment assignment mechanisms. Motivated by these considerations, we develop federated methods to draw inferences on the average treatment effects of combined data across sites. Our methods first compute summary statistics locally using propensity scores and then aggregate these statistics across sites to obtain point and variance estimators of average treatment effects. We show that these estimators are consistent and asymptotically normal. To achieve these asymptotic properties, we find that the aggregation schemes need to account for the heterogeneity in treatment assignments and in outcomes across sites. We demonstrate the validity of our federated methods through a comparative study of two large medical claims databases.

Public Blockchain-Envisioned Security Scheme Using Post Quantum Lattice-Based Aggregate Signature for Internet of Drones Applications

Due to high effectiveness and robust security protocols, lattice-based cryptography becomes a very broadly applicable optimistic post-quantum technique that is recently used in public key cryptosystem. An aggregate signature scheme enables a party to bundle a set of signatures together into a single short cryptographic signature, which can be verified by any verifier using the public information. In this paper, we provide a lattice-based aggregate signature scheme where the security depends on the difficulty of the Ring Learning-with-Error (Ring-LWE) problem. Next, we use the basic scheme in Internet of Drones (IoD) applications using the blockchain technology for secure and transparent data storage. The detailed security analysis and comparative study show that the proposed scheme provides superior security including resistance to quantum attacks and is efficient as compared to the existing state of art approaches. The testbed experimental results and the blockchain simulation demonstrate that the proposed scheme can be applied in real-life drones applications.

DCNet: Large-Scale Point Cloud Semantic Segmentation With Discriminative and Efficient Feature Aggregation

The point cloud feature aggregation, which learns discriminative features from the disordered points, plays a key role for large-scale point cloud semantic segmentation. Most previous aggregation methods are based on sampling a representative point subset, i.e., by a carefully designed point density metric, facing expensive computation cost especially for large-scale point clouds. Even though speeding up the point sampling process is studied by several recent works, but the component points in the sampled subset are uncertain and may change randomly, thus leading to corrupted geometric structure and discarded edges for representing an object. Therefore, we propose the DCNet, which consists of a fast point random sampling based encoder-decoder structure and several fully connected layers for semantic segmentation. To overcome the key feature loss caused by random down-sampling, the DCNet develops two novel local feature aggregation schemes: Double attention and Consistent constraints, to learn features that are discriminative for the challenging scenarios as above. The former considers both topological and semantic similarity of neighboring points to generate attention features for discriminating classes with similar geometric structures. The latter develops class-consistent constraints between adjacent layers in the decoder stage, to guide each point to aggregate with high-level semantic features of points belonging to the same class from the previous layer, which is beneficial for distinguishing neighboring points of the same class on the boundary. We conduct experiments and compare the proposed DCNet with existing methods on two benchmarks S3DIS and Semantic3D. Experiments show that the mean Intersection-over-Union (mIoU) of our method outperforms state-of-the-art methods by 2-3%, based on the same fast random sampling, and is also comparable to latest sampling-slower but accuracy-higher methods. That is, our method achieves the optimal speed-accuracy trade-off in the field of point cloud segmentation.