Hiding countermeasures are the most widely utilized techniques for thwarting side-channel attacks. Commonly, the Fisher-Yates algorithm is adopted in hiding countermeasures with permuted operation for its security and efficiency in implementation, yet the inherently sequential nature of the algorithm imposes limitations on hardware acceleration. In this work, we propose a novel method named Addition Round Rotation ($mathsf {ARR}$), which can introduce a time-area trade-off with block-based permutation. Our findings indicate that this approach can achieve a permutation brute force complexity level ranging from $2^{128}$, with the modified version achieving up to $2^{288}$ in a single clock cycle, while maintaining substantial resistance against second-order analysis. To substantiate the security of our proposed method, we introduce a new validation technique – Identity Verification. This technique allows theoretical validation of the proposed algorithm’s security and is consistent with the experimental results. Finally, we introduce an actual hardware design and provide the implementation results on Application-Specific Integrated Circuit (ASIC). The measured performance demonstrates that our proposal fully supports the practical applicability.
{"title":"Fully Parallel, One-Cycle Random Shuffling for Efficient Countermeasure Against Side Channel Attack and Its Complexity Verification","authors":"Jong-Yeon Park;Dongsoo Lee;Seonggyeom Kim;Wonil Lee;Bo Gyeong Kang;Kouichi Sakurai","doi":"10.1109/TETC.2024.3478228","DOIUrl":"https://doi.org/10.1109/TETC.2024.3478228","url":null,"abstract":"Hiding countermeasures are the most widely utilized techniques for thwarting side-channel attacks. Commonly, the Fisher-Yates algorithm is adopted in hiding countermeasures with permuted operation for its security and efficiency in implementation, yet the inherently sequential nature of the algorithm imposes limitations on hardware acceleration. In this work, we propose a novel method named Addition Round Rotation (<inline-formula><tex-math>$mathsf {ARR}$</tex-math></inline-formula>), which can introduce a time-area trade-off with block-based permutation. Our findings indicate that this approach can achieve a permutation brute force complexity level ranging from <inline-formula><tex-math>$2^{128}$</tex-math></inline-formula>, with the modified version achieving up to <inline-formula><tex-math>$2^{288}$</tex-math></inline-formula> in a single clock cycle, while maintaining substantial resistance against second-order analysis. To substantiate the security of our proposed method, we introduce a new validation technique – <i>Identity Verification</i>. This technique allows theoretical validation of the proposed algorithm’s security and is consistent with the experimental results. Finally, we introduce an actual hardware design and provide the implementation results on Application-Specific Integrated Circuit (ASIC). The measured performance demonstrates that our proposal fully supports the practical applicability.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 3","pages":"669-685"},"PeriodicalIF":5.4,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050804","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}
Pub Date : 2024-10-17DOI: 10.1109/TETC.2024.3479082
Eric Sturzinger;Jan Harkes;Padmanabhan Pillai;Mahadev Satyanarayanan
We introduce survival-critical machine learning (SCML), in which a robot encounters dynamically evolving threats that it recognizes via machine learning (ML), and then neutralizes. We model survivability in SCML, and show the value of the recently developed approach of Live Learning. This edge-based ML technique embodies an iterative human-in-the-loop workflow that concurrently enlarges the training set, trains the next model in a sequence of “best-so-far” models, and performs inferencing for both threat detection and pseudo-labeling. We present experimental results using datasets from the domains of drone surveillance, planetary exploration, and underwater sensing to quantify the effectiveness of Live Learning as a mechanism for SCML.
{"title":"Edge-Based Live Learning for Robot Survival","authors":"Eric Sturzinger;Jan Harkes;Padmanabhan Pillai;Mahadev Satyanarayanan","doi":"10.1109/TETC.2024.3479082","DOIUrl":"https://doi.org/10.1109/TETC.2024.3479082","url":null,"abstract":"We introduce <italic>survival-critical machine learning (SCML),</i> in which a robot encounters dynamically evolving threats that it recognizes via machine learning (ML), and then neutralizes. We model survivability in SCML, and show the value of the recently developed approach of <italic>Live Learning.</i> This edge-based ML technique embodies an iterative human-in-the-loop workflow that concurrently enlarges the training set, trains the next model in a sequence of “best-so-far” models, and performs inferencing for both threat detection and pseudo-labeling. We present experimental results using datasets from the domains of drone surveillance, planetary exploration, and underwater sensing to quantify the effectiveness of Live Learning as a mechanism for SCML.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 1","pages":"34-47"},"PeriodicalIF":5.1,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10721342","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-16DOI: 10.1109/TETC.2024.3472059
Fengqi Li;Jiaheng Wang;Weilin Xie;Ning Tong;Deguang Wang
The proliferation of IoT devices, advancements in edge computing, and innovations in AI technology have created an ideal environment for the birth and growth of Edge AI. With the trend towards the Internet of Everything (IoE), the EdgeAI- Human-IoT architectural framework highlights the necessity for efficient data exchange interconnectivity. Ensuring secure data sharing and efficient data storage are pivotal challenges in achieving seamless data interconnection. Owing to its simplicity, ease of deployment, and consensus-reaching capabilities, the RAFT consensus algorithm, which is commonly used in distributed storage, faces limitations as the IoT scale expands. The computational, communication, and storage capabilities of nodes are constraints, and the security of data remains a concern. To address these complex challenges, we introduce the X-RAFT consensus algorithm, which is tailored for blockchain technology. This algorithm enhances system performance and robustness, mitigates the impact of system load, enhances system sustainability, and increases Byzantine fault tolerance. Through analysis and simulations, our proposed solution has been evidenced to provide reliable security and efficient performance.
{"title":"X-RAFT: Improve RAFT Consensus to Make Blockchain Better Secure EdgeAI-Human-IoT Data","authors":"Fengqi Li;Jiaheng Wang;Weilin Xie;Ning Tong;Deguang Wang","doi":"10.1109/TETC.2024.3472059","DOIUrl":"https://doi.org/10.1109/TETC.2024.3472059","url":null,"abstract":"The proliferation of IoT devices, advancements in edge computing, and innovations in AI technology have created an ideal environment for the birth and growth of Edge AI. With the trend towards the Internet of Everything (IoE), the EdgeAI- Human-IoT architectural framework highlights the necessity for efficient data exchange interconnectivity. Ensuring secure data sharing and efficient data storage are pivotal challenges in achieving seamless data interconnection. Owing to its simplicity, ease of deployment, and consensus-reaching capabilities, the RAFT consensus algorithm, which is commonly used in distributed storage, faces limitations as the IoT scale expands. The computational, communication, and storage capabilities of nodes are constraints, and the security of data remains a concern. To address these complex challenges, we introduce the X-RAFT consensus algorithm, which is tailored for blockchain technology. This algorithm enhances system performance and robustness, mitigates the impact of system load, enhances system sustainability, and increases Byzantine fault tolerance. Through analysis and simulations, our proposed solution has been evidenced to provide reliable security and efficient performance.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 1","pages":"22-33"},"PeriodicalIF":5.1,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570701","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}
In order to protect the sensitive information in many applications involving neural networks, several privacy-preserving neural networks that operate on encrypted data have been developed. Unfortunately, existing encryption-based privacy-preserving neural networks are mainly built on classical cryptography primitives, which are not secure from the threat of quantum computing. In this paper, we propose the first quantum-resistant solution to protect neural network inferences based on an inner-product functional encryption scheme. The selected state-of-the-art functional encryption scheme based on lattice-based cryptography works with integer-type inputs, which is not directly compatible with neural network computations that operate in the floating point domain. We propose a polynomial-based secure convolution layer to allow a neural network to resolve this problem, along with a technique that reduces memory consumption. The proposed solution, named QuripfeNet, was applied in LeNet-5 and evaluated using the MNIST dataset. In a single-threaded implementation (CPU), QuripfeNet took 107.4 seconds for an inference to classify one image, achieving accuracy of 97.85%, which is very close to the unencrypted version. Additionally, the GPU-optimized QuripfeNet took 25.9 seconds to complete the same task, which is improved by 4.15× compared to the CPU version.
{"title":"QuripfeNet: Quantum-Resistant IPFE-Based Neural Network","authors":"KyungHyun Han;Wai-Kong Lee;Angshuman Karmakar;Myung-Kyu Yi;Seong Oun Hwang","doi":"10.1109/TETC.2024.3479193","DOIUrl":"https://doi.org/10.1109/TETC.2024.3479193","url":null,"abstract":"In order to protect the sensitive information in many applications involving neural networks, several privacy-preserving neural networks that operate on encrypted data have been developed. Unfortunately, existing encryption-based privacy-preserving neural networks are mainly built on classical cryptography primitives, which are not secure from the threat of quantum computing. In this paper, we propose the first quantum-resistant solution to protect neural network inferences based on an inner-product functional encryption scheme. The selected state-of-the-art functional encryption scheme based on lattice-based cryptography works with integer-type inputs, which is not directly compatible with neural network computations that operate in the floating point domain. We propose a polynomial-based secure convolution layer to allow a neural network to resolve this problem, along with a technique that reduces memory consumption. The proposed solution, named QuripfeNet, was applied in LeNet-5 and evaluated using the MNIST dataset. In a single-threaded implementation (CPU), QuripfeNet took 107.4 seconds for an inference to classify one image, achieving accuracy of 97.85%, which is very close to the unencrypted version. Additionally, the GPU-optimized QuripfeNet took 25.9 seconds to complete the same task, which is improved by 4.15× compared to the CPU version.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 3","pages":"640-653"},"PeriodicalIF":5.4,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051084","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}
The Smith-Waterman algorithm, which is founded on a dynamic programming approach, serves as a precise tool for aligning biological sequences. Despite its utility, the algorithm grapples with computational complexity and resource demands. Various implementations across multi-core, GPU, and FPGA platforms have sought to expedite the algorithm, yet frequently encounter issues such as suboptimal speedup, heightened reliance on external memory resources, and an exclusive focus on the forward step of the algorithm. To tackle these challenges, this study introduces an architecture aimed at accelerating the Smith-Waterman algorithm on FPGA platforms. Our architecture capitalizes on a pipeline structure that integrates optimized circuitry for parallel computations and employs memory allocation techniques, thus delivering an efficient, low power and cost-effective implementation for biological sequence alignment. Our assessments, coupled with comparisons against alternative FPGA implementations supporting protein sequence alignment, reveal a 17% increase in operating frequency and a 17% enhancement in Giga cell updates per second. Moreover, our approach competes with GPU-based solutions, showcasing comparable performance metrics alongside superior energy efficiency, with a 35% improvement. We substantiate the utility and performance of our pipeline architecture on FPGA platforms using four benchmark datasets. The validation results demonstrate a speedup ranging from 10 to 45 times for alignment score computation compared to the CPU platform.
{"title":"Pip-SW: Pipeline Architectures for Accelerating Smith-Waterman Algorithm on FPGA Platforms","authors":"Mahmood Kalemati;Ali Dehghan Nayeri;Somayyeh Koohi","doi":"10.1109/TETC.2024.3472649","DOIUrl":"https://doi.org/10.1109/TETC.2024.3472649","url":null,"abstract":"The Smith-Waterman algorithm, which is founded on a dynamic programming approach, serves as a precise tool for aligning biological sequences. Despite its utility, the algorithm grapples with computational complexity and resource demands. Various implementations across multi-core, GPU, and FPGA platforms have sought to expedite the algorithm, yet frequently encounter issues such as suboptimal speedup, heightened reliance on external memory resources, and an exclusive focus on the forward step of the algorithm. To tackle these challenges, this study introduces an architecture aimed at accelerating the Smith-Waterman algorithm on FPGA platforms. Our architecture capitalizes on a pipeline structure that integrates optimized circuitry for parallel computations and employs memory allocation techniques, thus delivering an efficient, low power and cost-effective implementation for biological sequence alignment. Our assessments, coupled with comparisons against alternative FPGA implementations supporting protein sequence alignment, reveal a 17% increase in operating frequency and a 17% enhancement in Giga cell updates per second. Moreover, our approach competes with GPU-based solutions, showcasing comparable performance metrics alongside superior energy efficiency, with a 35% improvement. We substantiate the utility and performance of our pipeline architecture on FPGA platforms using four benchmark datasets. The validation results demonstrate a speedup ranging from 10 to 45 times for alignment score computation compared to the CPU platform.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 3","pages":"628-639"},"PeriodicalIF":5.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050811","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}
Pub Date : 2024-10-11DOI: 10.1109/TETC.2024.3474856
Michał Wroński;Elżbieta Burek;Mateusz Leśniak
The security level of a cipher is a key parameter. While general-purpose quantum computers significantly threaten modern symmetric ciphers, other quantum approaches like quantum annealing have been less concerning. However, this paper argues that a quantum annealer specifically designed to attack Grain 128 and Grain 128a ciphers could soon be technologically feasible. Such an annealer would require 5,751 (6,761) qubits and 77,496 (94,865) couplers, with a qubit connectivity of 225 (245). This work also shows that modern stream ciphers like Grain 128 and Grain 128a may be vulnerable to quantum annealing attacks. Although the exact complexity of quantum annealing is unknown, heuristic estimates suggest that for many problems with $N$ variables, a $sqrt{N}$ exponential advantage over simulated annealing may hold. We detail how to transform algebraic attacks on Grain ciphers into the QUBO problem, making our attack potentially more efficient than classical brute-force methods. We demonstrate that applying our attack to rescaled Grain cipher versions, Grain $l$ and Grain $la$, overtakes brute-force and Grover’s attacks for sufficiently large $l$, assuming quantum annealing’s exponential benefit over simulated annealing.
{"title":"(In)security of Stream Ciphers Against Quantum Annealing Attacks on the Example of the Grain 128 and Grain 128a Ciphers","authors":"Michał Wroński;Elżbieta Burek;Mateusz Leśniak","doi":"10.1109/TETC.2024.3474856","DOIUrl":"https://doi.org/10.1109/TETC.2024.3474856","url":null,"abstract":"The security level of a cipher is a key parameter. While general-purpose quantum computers significantly threaten modern symmetric ciphers, other quantum approaches like quantum annealing have been less concerning. However, this paper argues that a quantum annealer specifically designed to attack Grain 128 and Grain 128a ciphers could soon be technologically feasible. Such an annealer would require 5,751 (6,761) qubits and 77,496 (94,865) couplers, with a qubit connectivity of 225 (245). This work also shows that modern stream ciphers like Grain 128 and Grain 128a may be vulnerable to quantum annealing attacks. Although the exact complexity of quantum annealing is unknown, heuristic estimates suggest that for many problems with <inline-formula><tex-math>$N$</tex-math></inline-formula> variables, a <inline-formula><tex-math>$sqrt{N}$</tex-math></inline-formula> exponential advantage over simulated annealing may hold. We detail how to transform algebraic attacks on Grain ciphers into the QUBO problem, making our attack potentially more efficient than classical brute-force methods. We demonstrate that applying our attack to rescaled Grain cipher versions, Grain <inline-formula><tex-math>$l$</tex-math></inline-formula> and Grain <inline-formula><tex-math>$la$</tex-math></inline-formula>, overtakes brute-force and Grover’s attacks for sufficiently large <inline-formula><tex-math>$l$</tex-math></inline-formula>, assuming quantum annealing’s exponential benefit over simulated annealing.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 3","pages":"614-627"},"PeriodicalIF":5.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051023","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}
Pub Date : 2024-10-11DOI: 10.1109/TETC.2024.3475214
Laura Carnevali;Marco Paolieri;Riccardo Reali;Leonardo Scommegna;Enrico Vicario
Software rejuvenation is a proactive maintenance technique that counteracts software aging by restarting a system, making selection of rejuvenation times critical to improve reliability without incurring excessive downtime costs. Various stochastic models of Software Aging and Rejuvenation (SAR) have been developed, mostly having an underlying stochastic process in the class of Continuous Time Markov Chains (CTMCs), Semi-Markov Processes (SMPs), and Markov Regenerative Processes (MRGPs) under the enabling restriction, requiring that at most one general (GEN), i.e., non-Exponential, timer be enabled in each state. We present a SAR model with an underlying MRGP under the bounded regeneration restriction, allowing for multiple GEN timers to be concurrently enabled in each state. This expressivity gain not only supports more accurate fitting of duration distributions from observed statistics, but also enables the definition of mixed rejuvenation strategies combining time-based and inspection-based policies, where the time to the next inspection or rejuvenation depends on the outcomes of diagnostic tests. Experimental results show that replacing GEN timers with Exponential timers with the same mean (to satisfy the enabling restriction) yields inaccurate rejuvenation policies, and that mixed rejuvenation outperforms time-based rejuvenation in maximizing reliability, though at the cost of an acceptable decrease in availability.
{"title":"Cost-Effective Software Rejuvenation Combining Time-Based and Inspection-Based Policies","authors":"Laura Carnevali;Marco Paolieri;Riccardo Reali;Leonardo Scommegna;Enrico Vicario","doi":"10.1109/TETC.2024.3475214","DOIUrl":"https://doi.org/10.1109/TETC.2024.3475214","url":null,"abstract":"Software rejuvenation is a proactive maintenance technique that counteracts software aging by restarting a system, making selection of rejuvenation times critical to improve reliability without incurring excessive downtime costs. Various stochastic models of Software Aging and Rejuvenation (SAR) have been developed, mostly having an underlying stochastic process in the class of Continuous Time Markov Chains (CTMCs), Semi-Markov Processes (SMPs), and Markov Regenerative Processes (MRGPs) under the enabling restriction, requiring that at most one general (GEN), i.e., non-Exponential, timer be enabled in each state. We present a SAR model with an underlying MRGP under the bounded regeneration restriction, allowing for multiple GEN timers to be concurrently enabled in each state. This expressivity gain not only supports more accurate fitting of duration distributions from observed statistics, but also enables the definition of mixed rejuvenation strategies combining time-based and inspection-based policies, where the time to the next inspection or rejuvenation depends on the outcomes of diagnostic tests. Experimental results show that replacing GEN timers with Exponential timers with the same mean (to satisfy the enabling restriction) yields inaccurate rejuvenation policies, and that mixed rejuvenation outperforms time-based rejuvenation in maximizing reliability, though at the cost of an acceptable decrease in availability.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 2","pages":"354-369"},"PeriodicalIF":5.1,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10715525","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144323147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1109/TETC.2024.3471458
Cláudio G. S. Capanema;Allan M. de Souza;Joahannes B. D. da Costa;Fabrício A. Silva;Leandro A. Villas;Antonio A. F. Loureiro
Researchers have studied how to improve Federated Learning (FL) in various areas, such as statistical and system heterogeneity, communication cost, and privacy. So far, most of the proposed solutions are either very tied to the application context or complex to be broadly reproduced in real-life applications involving humans. Developing modular solutions that can be leveraged by the vast majority of FL structures and are independent of the application people use is the new research direction opened by this paper. In this work, we propose a plugin (named FedPredict) to address three problems simultaneously: data heterogeneity, low performance of new/untrained and/or outdated clients, and communication cost. We do so mainly by combining global and local parameters (which brings generalization and personalization) in the inference step while adapting layer selection and matrix factorization techniques to reduce the downlink communication cost (server to client). Due to its simplicity, it can be applied to federated learning of different number of topologies. Results show that adding the proposed plugin to a given FL solution can significantly reduce the downlink communication cost by up to 83.3% and improve accuracy by up to 304% compared to the original solution.
{"title":"A Novel Prediction Technique for Federated Learning","authors":"Cláudio G. S. Capanema;Allan M. de Souza;Joahannes B. D. da Costa;Fabrício A. Silva;Leandro A. Villas;Antonio A. F. Loureiro","doi":"10.1109/TETC.2024.3471458","DOIUrl":"https://doi.org/10.1109/TETC.2024.3471458","url":null,"abstract":"Researchers have studied how to improve Federated Learning (FL) in various areas, such as statistical and system heterogeneity, communication cost, and privacy. So far, most of the proposed solutions are either very tied to the application context or complex to be broadly reproduced in real-life applications involving humans. Developing modular solutions that can be leveraged by the vast majority of FL structures and are independent of the application people use is the new research direction opened by this paper. In this work, we propose a plugin (named FedPredict) to address three problems simultaneously: data heterogeneity, low performance of new/untrained and/or outdated clients, and communication cost. We do so mainly by combining global and local parameters (which brings generalization and personalization) in the inference step while adapting layer selection and matrix factorization techniques to reduce the downlink communication cost (server to client). Due to its simplicity, it can be applied to federated learning of different number of topologies. Results show that adding the proposed plugin to a given FL solution can significantly reduce the downlink communication cost by up to 83.3% and improve accuracy by up to 304% compared to the original solution.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 1","pages":"5-21"},"PeriodicalIF":5.1,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570650","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}
Pub Date : 2024-10-10DOI: 10.1109/TETC.2024.3474484
Enrique Mármol Campos;Aurora Gonzalez-Vidal;José L. Hernández-Ramos;Antonio Skarmeta
Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks, which can significantly degrade model performance and hinder convergence. The effectiveness of existing approaches to mitigate complex attacks, such as median, trimmed mean, or Krum aggregation functions, has been only partially demonstrated in the case of specific attacks. Our study introduces a novel robust aggregation mechanism utilizing the Fourier Transform (FT), which is able to effectively handle sophisticated attacks without prior knowledge of the number of attackers. Employing this data technique, weights generated by FL clients are projected into the frequency domain to ascertain their density function, selecting the one exhibiting the highest frequency. Consequently, malicious clients’ weights are excluded. Our proposed approach was tested against various model poisoning attacks, demonstrating superior performance over state-of-the-art aggregation methods.
{"title":"FedRDF: A Robust and Dynamic Aggregation Function Against Poisoning Attacks in Federated Learning","authors":"Enrique Mármol Campos;Aurora Gonzalez-Vidal;José L. Hernández-Ramos;Antonio Skarmeta","doi":"10.1109/TETC.2024.3474484","DOIUrl":"https://doi.org/10.1109/TETC.2024.3474484","url":null,"abstract":"Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks, which can significantly degrade model performance and hinder convergence. The effectiveness of existing approaches to mitigate complex attacks, such as median, trimmed mean, or Krum aggregation functions, has been only partially demonstrated in the case of specific attacks. Our study introduces a novel robust aggregation mechanism utilizing the Fourier Transform (FT), which is able to effectively handle sophisticated attacks without prior knowledge of the number of attackers. Employing this data technique, weights generated by FL clients are projected into the frequency domain to ascertain their density function, selecting the one exhibiting the highest frequency. Consequently, malicious clients’ weights are excluded. Our proposed approach was tested against various model poisoning attacks, demonstrating superior performance over state-of-the-art aggregation methods.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 1","pages":"48-67"},"PeriodicalIF":5.1,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713851","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1109/TETC.2024.3473911
Quy Vu Khanh;Abdellah Chehri;Van Anh Dang;Quy Nguyen Minh
Across all periods of human history, the importance attributed to health has remained a fundamental and significant facet. This statement holds greater validity within the present context. The pressing demand for healthcare solutions with real-time capabilities, affordability, and high precision is crucial in medical research and technology progress. In recent times, there has been a significant advancement in emerging technologies such as AI, IoT, blockchain, and edge computing. These breakthrough developments have led to the creation of various intelligent applications. Smart healthcare applications can be realized by combining robust AI detection and prediction capabilities with edge computing architecture, which offers low computing costs and latency. In this paper, we begin by conducting a literature review of AI-assisted EC-based smart healthcare applications from the past three years. Our goal is to identify gaps and barriers in this field. We propose a smart healthcare architecture model that integrates AI technology into the edge. Finally, we summarize the challenges and research directions associated with the proposed model.
{"title":"Federated Learning Approach for Collaborative and Secure Smart Healthcare Applications","authors":"Quy Vu Khanh;Abdellah Chehri;Van Anh Dang;Quy Nguyen Minh","doi":"10.1109/TETC.2024.3473911","DOIUrl":"https://doi.org/10.1109/TETC.2024.3473911","url":null,"abstract":"Across all periods of human history, the importance attributed to health has remained a fundamental and significant facet. This statement holds greater validity within the present context. The pressing demand for healthcare solutions with real-time capabilities, affordability, and high precision is crucial in medical research and technology progress. In recent times, there has been a significant advancement in emerging technologies such as AI, IoT, blockchain, and edge computing. These breakthrough developments have led to the creation of various intelligent applications. Smart healthcare applications can be realized by combining robust AI detection and prediction capabilities with edge computing architecture, which offers low computing costs and latency. In this paper, we begin by conducting a literature review of AI-assisted EC-based smart healthcare applications from the past three years. Our goal is to identify gaps and barriers in this field. We propose a smart healthcare architecture model that integrates AI technology into the edge. Finally, we summarize the challenges and research directions associated with the proposed model.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 1","pages":"68-79"},"PeriodicalIF":5.1,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570756","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：