| 1. |
- Ahlgren, Bengt, et al.
(författare)
-
Internet of Things for Smart Cities : Interoperability and Open Data
- 2016
-
Ingår i: IEEE Internet Computing. - : IEEE Computer Society. - 1089-7801 .- 1941-0131. ; 20:6, s. 52-56
-
Tidskriftsartikel (refereegranskat)abstract
- The Internet of Things (IoT) has become a promising technology for addressing societal challenges by connecting smart devices and leveraging Big Data analytics to create smart cities worldwide. As the IoT scales up, it's important to provide interoperability among different devices. Yet current simple standard protocols lack sufficient openness and interoperability. IoT for smart cities needs to guarantee the accessibility of open data and cloud services to allow industries and citizens to develop new services and applications. Here, the authors provide a case study of the GreenIoT platform in Uppsala, Sweden, to demonstrate the idea of interoperability and open data for smart cities.
|
|
| 2. |
- Borgh, Joakim, et al.
(författare)
-
Employing attribute-based encryption in systems with resource constrained devices in an information-centric networking context
- 2017
-
Ingår i: 2017 Global Internet of Things Summit (GIoTS). - : IEEE. - 9781509058730 ; , s. 397-402
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Attribute-Based Encryption (ABE) is considered to be one of the most promising ways to be enforce access control in Information-Centric Networking (ICN). As the Internet of Things (IoT) is being considered as one of the primary use cases for ICN it raises the question of the compatibility between IoT and ABE. An important part of the IoT is the resource constrained devices, for them there is a challenge to perform the computationally expensive operations required for ABE. In this paper we consider ABE in sensor networks and discuss the strengths and weaknesses of a system solution where the ABE operations are performed on the sensors. To properly discuss these concerns we have implemented two ABE schemes, a Single-authority ABE (SA-CP-ABE) scheme and a Multi-authority ABE (MA-CP-ABE) scheme. Results regarding the execution time, RAM usage, data overhead and battery consumption of these implementations on a sensor are presented. We conclude that it is possible, already today, to perform ABE on sensors for smaller policies. The main limitation in deploying ABE in sensors is the RAM size of the sensors.
|
|
| 3. |
|
|
| 4. |
- Chen, Weili, et al.
(författare)
-
Detecting Ponzi Schemes on Ethereum : Towards Healthier Blockchain Technology
- 2018
-
Ingår i: WWW '18. - New York, New York, USA : ACM Digital Library. - 9781450356398 ; , s. 1409-1418
-
Konferensbidrag (refereegranskat)abstract
- Blockchain technology becomes increasingly popular. It also attracts scams, for example, Ponzi scheme, a classic fraud, has been found making a notable amount of money on Blockchain, which has a very negative impact. To help dealing with this issue, this paper proposes an approach to detect Ponzi schemes on blockchain by using data mining and machine learning methods. By verifying smart contracts on Ethereum, we first extract features from user accounts and operation codes of the smart contracts and then build a classification model to detect latent Ponzi schemes implemented as smart contracts. The experimental results show that the proposed approach can achieve high accuracy for practical use. More importantly, the approach can be used to detect Ponzi schemes even at the moment of its creation. By using the proposed approach, we estimate that there are more than 400 Ponzi schemes running on Ethereum. Based on these results, we propose to build a uniform platform to evaluate and monitor every created smart contract for early warning of scams.
|
|
| 5. |
|
|
| 6. |
- Deng, Weipeng, et al.
(författare)
-
Energy-Efficient Monitoring of Potential Side Effects from COVID-19 Vaccines
- 2022
-
Ingår i: Proceedings. - : IEEE. - 9781665454179 - 9781665454186 ; , s. 222-227
-
Konferensbidrag (refereegranskat)abstract
- COVID-19 has affected the world for almost two years causing lots of damages and losses of lives. With the development of sensing technology and digital health, research studies suggest to use wearable devices for monitoring COVID-19 symptoms or analyzing people’s behaviour change. As COVID-19 vaccines are getting widely available, their side effects have raised public concerns, though have not yet been thoroughly studied due to the short deployment time. As far as we know, this work is the first study to use wearable devices and mobile app to collect physiological data to explore potential side effects to human bodies from COVID-19 vaccinations. We designed and developed a mobile sensing system, which can monitor changes of physiological indicators through wearable devices, collect self-reported data from the users and proposed a green data transmission mechanism which can reduce the communication overheads. Pilot study has been conducted to evaluate the feasibility of our system. Preliminary results show that increased resting heart rate (RHR) and changes on average heart rate (HR) are observed in some participants after COVID-19 vaccinations. This study opens up the opportunity to collect larger amount of data and further investigate potential side effects from COVID-19 vaccinations.
|
|
| 7. |
- Ekberg, Pontus, et al.
(författare)
-
A distributed swarm-intelligent localization for sensor networks with mobile nodes
- 2011
-
Ingår i: Proc. 7th International Wireless Communications and Mobile Computing Conference. - Piscataway, NJ : IEEE. - 9781424495399 ; , s. 83-88
-
Konferensbidrag (refereegranskat)abstract
- We present a novel distributed localization algorithm, called Swarm-Intelligent Localization (SIL), for computing the physical locations of nodes in wireless sensor networks. The algorithm assumes that only a small fraction of the nodes have a priori knowledge of their positions, and that noisy distance measurements are available between all neighboring nodes. The algorithm has no explicit global state and it can handle nodes that are both mobile and that can arrive in the network at any time. SIL works in two different phases, a coarse phase where nodes compute rough positions for themselves based on information about remote anchors, and a fine phase where nodes iteratively refine their positions from the coarse phase by collaborating with their neighbors. The average computational complexity per node running SIL is very low, namely constant in the network size and linear in the connectivity of the network. We evaluate the algorithm through extensive simulations. The results indicate that SIL is able to compute accurate positions for the majority of nodes in a wide range of network topologies and settings, and that it can handle difficulties such as large distance measurement errors and low network connectivity.
|
|
| 8. |
- Elsts, Atis, et al.
(författare)
-
A Case for Node-Local Runtime Parameter Adaptation in Wireless Sensor Networks
- 2014
-
Ingår i: Proc. 10th Swedish National Computer Networking Workshop.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- The challenges posed to wireless sensor networks by the environments they are deployed cannot always be predicted beforehand. Therefore, adaptive behavior at the run-time may be required to achieve good reliability and energy-efficiency. We present a node-local runtime adaptation algorithm that adapts the over-the-air message encoding based on presence of weak links and external interference in the immediate neighborhood of the node. Evaluation with a network simulator shows that this algorithm leads to significant network-wide reduction of radio duty cycle under specific radio transmission failure models.
|
|
| 9. |
- Fang, Jing, et al.
(författare)
-
Depression Prevalence in Postgraduate Students and Its Association With Gait Abnormality
- 2019
-
Ingår i: IEEE Access. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2169-3536. ; 7, s. 174425-174437
-
Tidskriftsartikel (refereegranskat)abstract
- In recent years, an increasing number of university students are found to be at high risk of depression. Through a large scale depression screening, this paper finds that around 6.5% of the university postgraduate students in China experience depression. We then investigate whether the gait patterns of these individuals have already changed as depression is suggested to associate with gait abnormality. Significant differences are found in several spatiotemporal, kinematic and postural gait parameters such as walking speed, stride length, head movement, vertical head posture, arm swing, and body sway, between the depressed and non-depressed groups. Applying these features to classifiers with different machine learning algorithms, we examine whether natural gait analysis may serve as a convenient and objective tool to assist in depression recognition. The results show that when using a random forest classifier, the two groups can be classified automatically with a maximum accuracy of 91.58%. Furthermore, a reasonable accuracy can already be achieved by using parameters from the upper body alone, indicating that upper body postures and movements can effectively contribute to depression analysis.
|
|
| 10. |
|
|
| 11. |
|
|
| 12. |
- Guerreiro, João, et al.
(författare)
-
Privacy-aware probabilistic sampling for data collection in wireless sensor networks
- 2011
-
Ingår i: Proc. 7th International Wireless Communications and Mobile Computing Conference. - Piscataway, NJ : IEEE conference proceedings. - 9781424495399 ; , s. 314-319
-
Konferensbidrag (refereegranskat)abstract
- The rising popularity of web services and their applications to sensor networks enables real-time data collection and queries by users. Unlike traditional periodic data collection, the traffic patterns generated from real-time data collection may expose the interests of users or the locations of unusual events to the attackers. To provide privacy in data collection, we propose a novel probabilistic sampling mechanism that can hide user queries and unusual events in the network, while supporting both routine and on-demand data reporting. Our goal is to prevent attackers from locating the unusual events and identifying interests of users by eavesdropping and analyzing the network traffic. In our probabilistic sampling scheme, the data are carefully reported at random times in order to mask the unusual events and user queries. In the meantime, our scheme can provide users with high data accuracy at minimized communication overheads. Extensive simulations have been conducted to evaluate the security strength, data accuracy and communication overheads of the proposed scheme.
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
- Hassani Bijarbooneh, Farshid, 1981-
(författare)
-
Constraint Programming for Wireless Sensor Networks
- 2015
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In recent years, wireless sensor networks (WSNs) have grown rapidly and have had a substantial impact in many applications. A WSN is a network that consists of interconnected autonomous nodes that monitor physical and environmental conditions, such as temperature, humidity, pollution, etc. If required, nodes in a WSN can perform actions to affect the environment.WSNs present an interesting and challenging field of research due to the distributed nature of the network and the limited resources of the nodes. It is necessary for a node in a WSN to be small to enable easy deployment in an environment and consume as little energy as possible to prolong its battery lifetime. There are many challenges in WSNs, such as programming a large number of nodes, designing communication protocols, achieving energy efficiency, respecting limited bandwidth, and operating with limited memory. WSNs are further constrained due to the deployment of the nodes in indoor and outdoor environments and obstacles in the environment.In this dissertation, we study some of the fundamental optimisation problems related to the programming, coverage, mobility, data collection, and data loss of WSNs, modelled as standalone optimisation problems or as optimisation problems integrated with protocol design. Our proposed solution methods come from various fields of research including constraint programming, integer linear programming, heuristic-based algorithms, and data inference techniques.
|
|
| 16. |
|
|
| 17. |
|
|
| 18. |
|
|
| 19. |
|
|
| 20. |
- Hermans, Frederik, et al.
(författare)
-
FOCUS : Robust Visual Codes for Everyone
- 2016. - 28
-
Ingår i: Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys 2016). - New York, NY, USA : ACM. - 9781450342698 ; , s. 319-332
-
Konferensbidrag (refereegranskat)abstract
- Visual codes are used to embed digital data in physical objects, or they are shown in video sequences to transfer data over screen/camera links. Existing codes either carry limited data to make them robust against a range of channel conditions (e.g., low camera quality or long distances), or they support a high data capacity but only work over a narrow range of channel conditions. We present Focus, a new code design that does not require this explicit trade-off between code capacity and the reader’s channel quality. Instead,Focus builds on concepts from OFDM to encode data at different levels of spatial detail. This enables each reader to decode as much data from a code as its channel quality allows. We build a prototype of Focus devices and evaluate it experimentally. Our results show that Focus gracefully adapts to the reader’s channel, and that it provides a significant performance improvement over recently proposed designs, including Strata and PixNet.
|
|
| 21. |
|
|
| 22. |
|
|
| 23. |
- Hermans, Frederik, et al.
(författare)
-
Poster Abstract:Supporting Heterogeneous LCD/Camera Links
- 2014. - 10
-
Ingår i: Proc. 13th International Symposium on Information Processing in Sensor Networks. - Piscataway, NJ : IEEE Press. - 9781479931460 ; , s. 289-290
-
Konferensbidrag (refereegranskat)abstract
- Visible light communication over LCD/camera links offers a potential complement to traditional RF communication technology such as WiFi or cellular networks. However, the heterogeneity in receivers (e.g., mobile phone cameras) presents a challenge because the receivers differ widely in resolution, distance to the transmitter (LCD), and other factors, and therefore they differ in channel quality. We are researching a communication scheme in which each receiver can decode as much data from an LCD's transmission as the receiver's channel supports. The core idea is to encode the payload into an image's frequency representation rather than directly into pixels. We have successfully transmitted data using a prototype implementation and are currently investigating appropriate channel models.
|
|
| 24. |
|
|
| 25. |
- Hermans, Frederik
(författare)
-
Sensor Networks and Their Radio Environment : On Testbeds, Interference, and Broken Packets
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Sensor networks consist of small sensing devices that collaboratively fulfill a sensing task, such as monitoring the soil in an agricultural field or measuring vital signs in a marathon runner. To avoid cumbersome and expensive cabling, nodes in a sensor network are powered by batteries and communicate wirelessly. As a consequence of the latter, a sensor network's communication is affected by its radio environment, i.e., the environment's propagation characteristics and the presence of other radio devices. This thesis addresses three issues related to the impact of the radio environment on sensor networks.Firstly, in order to draw conclusions from experimental results, it is necessary to assess how the environment and the experiment infrastructure affect the results. We design a sensor network testbed, dubbed Sensei-UU, to be easily relocatable. By performing an experiment in different environments, a researcher can asses the environments’ impact on results. We further augment Sensei-UU with support for mobile nodes. The implemented mobility approach adds only little variance to results, and therefore enables repeatable experiments with mobility. The repeatability of experiments increases the confidence in conclusions drawn from them.Secondly, sensor networks may experience poor communication performance due to cross-technology radio interference, especially in office and residential environments. We consider the problem of detecting and classifying the type of interference a sensor network is exposed to. We find that different sources of interference each leave a characteristic "fingerprint" on individual, corrupt 802.15.4 packets. We design and implement the SoNIC system that enables sensor nodes to classify interference using these fingerprints. SoNIC supports accurate classification in both a controlled and an uncontrolled environment.Finally, we consider transmission errors in an outdoor sensor network. In such an environment, errors occur despite the absence of interference if the signal-to-noise ratio at a receiver is too low. We study the characteristics of corrupt packets collected from an outdoor sensor network deployment. We find that content transformation in corrupt packets follows a specific pattern, and that most corrupt packets contain only few errors. We propose that the pattern may be useful for applications that can operate on inexact data, because it reduces the uncertainty associated with a corrupt packet.
|
|
| 26. |
- Hermans, Frederik, et al.
(författare)
-
SoNIC: Classifying Interference in 802.15.4 Sensor Networks
- 2013. - 11
-
Ingår i: Proc. 12th International Conference on Information Processing in Sensor Networks. - New York, NY, USA : ACM. - 9781450319591 ; , s. 55-66
-
Konferensbidrag (refereegranskat)abstract
- Sensor networks that operate in the unlicensed 2.4 GHz frequency band suffer cross-technology radio interference from a variety of devices, e.g., Bluetooth headsets, laptops using WiFi, or microwave ovens. Such interference has been shown to significantly degrade network performance. We present SoNIC, a system that enables resource-limited sensor nodes to detect the type of interference they are exposed to and select an appropriate mitigation strategy. The key insight underlying SoNIC is that different interferers disrupt individual 802.15.4 packets in characteristic ways that can be detected by sensor nodes. In contrast to existing approaches to interference detection, SoNIC does not rely on active spectrum sampling or additional hardware, making it lightweight and energy-efficient. In an office environment with multiple interferers, a sensor node running SoNIC correctly detects the predominant interferer 87% of the time. To show how sensor networks can benefit from SoNIC, we add it to a mobile sink application to improve the application's packet reception ratio under interference.
|
|
| 27. |
|
|
| 28. |
|
|
| 29. |
- Hu, Xiping, et al.
(författare)
-
Crowdsourcing for Mobile Networks and IoT
- 2018
-
Ingår i: Wireless Communications & Mobile Computing. - : WILEY-HINDAWI. - 1530-8669 .- 1530-8677.
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 30. |
|
|
| 31. |
|
|
| 32. |
- Hu, Xiping, et al.
(författare)
-
SAfeDJ : A crowd-cloud codesign approach to situation-aware music delivery for drivers
- 2015
-
Ingår i: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP). - : Association for Computing Machinery (ACM). - 1551-6857 .- 1551-6865. ; 12:1s, s. 21:1-24
-
Tidskriftsartikel (refereegranskat)abstract
- Driving is an integral part of our everyday lives, but it is also a time when people are uniquely vulnerable. Previous research has demonstrated that not only does listening to suitable music while driving not impair driving performance, but it could lead to an improved mood and a more relaxed body state, which could improve driving performance and promote safe driving significantly. In this article, we propose SAfeDJ, a smartphone-based situation-aware music recommendation system, which is designed to turn driving into a safe and enjoyable experience. SAfeDJ aims at helping drivers to diminish fatigue and negative emotion. Its design is based on novel interactive methods, which enable in-car smartphones to orchestrate multiple sources of sensing data and the drivers' social context, in collaboration with cloud computing to form a seamless crowdsensing solution. This solution enables different smartphones to collaboratively recommend preferable music to drivers according to each driver's specific situations in an automated and intelligent manner. Practical experiments of SAfeDJ have proved its effectiveness in music-mood analysis, and mood-fatigue detections of drivers with reasonable computation and communication overheads on smartphones. Also, our user studies have demonstrated that SAfeDJ helps to decrease fatigue degree and negative mood degree of drivers by 49.09% and 36.35%, respectively, compared to traditional smartphone-based music player under similar driving situations.
|
|
| 33. |
|
|
| 34. |
|
|
| 35. |
|
|
| 36. |
- Huang, Weiwei, et al.
(författare)
-
Buffer State is Enough : Simplifying the Design of QoE-Aware HTTP Adaptive Video Streaming
- 2018
-
Ingår i: IEEE transactions on broadcasting. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 0018-9316 .- 1557-9611. ; 64:2, s. 590-601
-
Tidskriftsartikel (refereegranskat)abstract
- Recently, the prevalence of mobile devices together with the outburst of user-generated contents has fueled the tremendous growth of the Internet traffic taken by video streaming. To improve user-perceived quality-of-experience (QoE), dynamic adaptive streaming via HTTP (DASH) has been widely adopted by practical systems to make streaming smooth under limited bandwidth. However, previous DASH approaches mostly performed complicated rate adaptation based on bandwidth estimation, which has been proven to be unreliable over HTTP. In this paper, we simplify the design by only exploiting client-side buffer state information and propose a pure buffer-based DASH scheme to optimize user QoE. Our approach can not only get rid of the drawback caused by inaccurate bandwidth estimation, but also incur very limited overhead. We explicitly define an integrated user QoE model, which takes playback freezing, bitrate switch, and video quality into account, and then formulate the problem into a non-linear stochastic optimal control problem. Next, we utilize control theory to design a dynamic buffer-based controller for DASH, which determines video bitrate of each chunk to be requested and stabilize the buffer level in the meanwhile. Extensive experiments have been conducted to validate the advantages of our approach, and the results show that our approach can achieve the best performance compared with other alternative approaches.
|
|
| 37. |
|
|
| 38. |
|
|
| 39. |
- Jiang, Zhihan, et al.
(författare)
-
Leveraging Machine Learning for Disease Diagnoses based on Wearable Devices : A Survey
- 2023
-
Ingår i: IEEE Internet of Things Journal. - : Institute of Electrical and Electronics Engineers (IEEE). - 2327-4662. ; 10:24, s. 21959-21981
-
Tidskriftsartikel (refereegranskat)abstract
- Many countries around the world are facing a shortage of healthcare resources, especially during the post-epidemic era, leading to a dramatic increase in the need for self-detection and self-management of diseases. The popularity of smart wearable devices, such as smartwatches, and the development of machine learning bring new opportunities for the early detection and management of various prevalent diseases, such as cardiovascular diseases, Parkinson’s disease, and diabetes. In this survey, we comprehensively review the articles related to specific diseases or health issues based on small wearable devices and machine learning. More specifically, we first present an overview of the articles selected and classify them according to their targeted diseases. Then, we summarize their objectives, wearable device and sensor data, machine learning techniques, and wearing locations. Based on the literature review, we discuss the challenges and propose future directions from the perspectives of privacy concerns, security concerns, transmission latency and reliability, energy consumption, multi-modality, multi-sensor, multi-devices, evaluation metrics, explainability, generalization and personalization, social influence, and human factors, aiming to inspire researchers in this field.
|
|
| 40. |
- Kaivonen, Sami, et al.
(författare)
-
Real-time air pollution monitoring with sensors on city bus
- 2020
-
Ingår i: Digital Communications and Networks. - : KeAi. - 2468-5925 .- 2352-8648. ; 6:1, s. 23-30
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents an experimental study on real-time air pollution monitoring using wireless sensors on public transport vehicles. The study is part of the GreenIoT project in Sweden, which utilizes Internet-of-Things to measure air pollution level in the city center of Uppsala. Through deploying low-cost wireless sensors, it is possible to obtain more fine-grained and real-time air pollution levels at different locations. The sensors on public transport vehicles complement the readings from stationary sensors and the only ground level monitoring station in Uppsala. The paper describes the deployment of wireless sensors on Uppsala buses and the integration of the mobile sensor network with the GreenIoT testbed. Extensive experiments have been conducted to evaluate the communication quality and data quality of the system.
|
|
| 41. |
- Ke, Yihao, et al.
(författare)
-
GECKO : Gamer Experience-Centric Bitrate Control Algorithm for Cloud Gaming
- 2017
-
Ingår i: Image and Graphics. - Cham : Springer. - 9783319715896 - 9783319715889 ; , s. 325-335
-
Konferensbidrag (refereegranskat)abstract
- Cloud gaming considered as the future of computer games enables users to play high-end games on resource-constrained heterogeneous devices. Games are rendered on remote clouds and delivered to users via the Internet in the form of video streaming, which can dramatically reduce the consumption of client-side resources. However, such service needs high bandwidth connections to make the game streaming smooth, which is already a major issue to hamper the prevalence of cloud gaming. In this paper, we propose a gamer experience-centric bitrate control algorithm called GECKO, to reduce the consumption of bandwidth resources for cloud gaming while only slightly impairing user quality-of-experience (QoE). Through measurement studies, we find that user QoE is mainly determined by the ROI (Region of Interest) size and QP offset. Hence, in order to save bandwidth consumption without severely impairing user QoE, we can lower the quality of the region outside of ROI. Our proposed GECKO algorithm is designed to adaptively tune the size of ROI and the quality of the outside region. We implement the GECKO algorithm on a real cloud gaming platform. The experiment results show that over 15.8% bandwidth can be saved compared with state-of-the-art approaches.
|
|
| 42. |
|
|
| 43. |
- Leung, Victor C. M., et al.
(författare)
-
Editorial for QShine 2014 Special Issue
- 2016
-
Ingår i: Mobile Networks and Applications. - : Springer Science and Business Media LLC. - 1383-469X .- 1572-8153. ; 21:3, s. 387-389
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 44. |
- Li, Shenghui, 1994-, et al.
(författare)
-
An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning
- 2023
-
Ingår i: IEEE Transactions on Big Data. - : Institute of Electrical and Electronics Engineers (IEEE). - 2332-7790 .- 2372-2096.
-
Tidskriftsartikel (refereegranskat)abstract
- Byzantine-robust federated learning aims at mitigating Byzantine failures during the federated training process, where malicious participants (known as Byzantine clients) may upload arbitrary local updates to the central server in order to degrade the performance of the global model. In recent years, several robust aggregation schemes have been proposed to defend against malicious updates from Byzantine clients and improve the robustness of federated learning. These solutions were claimed to be Byzantine-robust, under certain assumptions. Other than that, new attack strategies are emerging, striving to circumvent the defense schemes. However, there is a lack of systematical comparison and empirical study thereof. In this paper, we conduct an experimental study of Byzantine-robust aggregation schemes under different attacks using two popular algorithms in federated learning, FedSGD and FedAvg . We first survey existing Byzantine attack strategies, as well as Byzantine-robust aggregation schemes that aim to defend against Byzantine attacks. We also propose a new scheme, ClippedClustering, to enhance the robustness of a clustering-based scheme by automatically clipping the updates. Then we provide an experimental evaluation of eight aggregation schemes in the scenario of five different Byzantine attacks. Our experimental results show that these aggregation schemes sustain relatively high accuracy in some cases, but they are not effective in all cases. In particular, our proposed ClippedClustering successfully defends against most attacks under independent and identically distributed (IID) local datasets. However, when the local datasets are Non-IID, the performance of all the aggregation schemes significantly decreases. With Non-IID data, some of these aggregation schemes fail even in the complete absence of Byzantine clients. Based on our experimental study, we conclude that the robustness of all the aggregation schemes is limited, highlighting the need for new defense strategies, in particular for Non-IID datasets.
|
|
| 45. |
- Li, Shenghui, 1994-, et al.
(författare)
-
Auto-Weighted Robust Federated Learning with Corrupted Data Sources
- 2022
-
Ingår i: ACM Transactions on Intelligent Systems and Technology. - : Association for Computing Machinery. - 2157-6904 .- 2157-6912. ; 13:5
-
Tidskriftsartikel (refereegranskat)abstract
- Federated learning provides a communication-efficient and privacy-preserving training process by enabling learning statistical models with massive participants without accessing their local data. Standard federated learning techniques that naively minimize an average loss function are vulnerable to data corruptions from outliers, systematic mislabeling, or even adversaries. In this article, we address this challenge by proposing Auto-weighted Robust Federated Learning (ARFL), a novel approach that jointly learns the global model and the weights of local updates to provide robustness against corrupted data sources. We prove a learning bound on the expected loss with respect to the predictor and the weights of clients, which guides the definition of the objective for robust federated learning. We present an objective that minimizes the weighted sum of empirical risk of clients with a regularization term, where the weights can be allocated by comparing the empirical risk of each client with the average empirical risk of the best ( p ) clients. This method can downweight the clients with significantly higher losses, thereby lowering their contributions to the global model. We show that this approach achieves robustness when the data of corrupted clients is distributed differently from the benign ones. To optimize the objective function, we propose a communication-efficient algorithm based on the blockwise minimization paradigm. We conduct extensive experiments on multiple benchmark datasets, including CIFAR-10, FEMNIST, and Shakespeare, considering different neural network models. The results show that our solution is robust against different scenarios, including label shuffling, label flipping, and noisy features, and outperforms the state-of-the-art methods in most scenarios.
|
|
| 46. |
- Li, Shenghui, 1994-, et al.
(författare)
-
Blades : A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning
- 2024
-
Konferensbidrag (refereegranskat)abstract
- Federated learning (FL) facilitates distributed training across different IoT and edge devices, safeguarding the privacy of their data. The inherent distributed structure of FL introduces vulnerabilities, especially from adversarial devices aiming to skew local updates to their advantage. Despite the plethora of research focusing on Byzantine-resilient FL, the academic community has yet to establish a comprehensive benchmark suite, pivotal for impartial assessment and comparison of different techniques. This paper presents Blades, a scalable, extensible, and easily configurable benchmark suite that supports researchers and developers in efficiently implementing and validating novel strategies against baseline algorithms in Byzantine-resilient FL. Blades contains built-in implementations of representative attack and defense strategies and offers a user-friendly interface that seamlessly integrates new ideas. Using Blades, we re-evaluate representative attacks and defenses on wide-ranging experimental configurations (approximately 1,500 trials in total). Through our extensive experiments, we gained new insights into FL robustness and highlighted previously overlooked limitations due to the absence of thorough evaluations and comparisons of baselines under various attack settings. We maintain the source code and documents at https://github.com/lishenghui/blades.
|
|
| 47. |
- Li, Shenghui, 1994-, et al.
(författare)
-
Byzantine-Robust Aggregation in Federated Learning Empowered Industrial IoT
- 2023
-
Ingår i: IEEE Transactions on Industrial Informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 1551-3203 .- 1941-0050. ; 19:2, s. 1165-
-
Tidskriftsartikel (refereegranskat)abstract
- Federated Learning (FL) is a promising paradigm to empower on-device intelligence in Industrial Internet of Things(IIoT) due to its capability of training machine learning models across multiple IIoT devices, while preserving the privacy of their local data. However, the distributed architecture of FL relies on aggregating the parameter list from the remote devices, which poses potential security risks caused by malicious devices. In this paper, we propose a flexible and robust aggregation rule, called Auto-weighted Geometric Median (AutoGM), and analyze the robustness against outliers in the inputs. To obtain the value of AutoGM, we design an algorithm based on alternating optimization strategy. Using AutoGM as aggregation rule, we propose two robust FL solutions, AutoGM_FL and AutoGM_PFL. AutoGM_FL learns a shared global model using the standard FL paradigm, and AutoGM_PFL learns a personalized model for each device. We conduct extensive experiments on the FEMNIST and Bosch IIoT datasets. The experimental results show that our solutions are robust against both model poisoning and data poisoning attacks. In particular, our solutions sustain high performance even when 30% of the nodes perform model or 50% of the nodes perform data poisoning attacks.
|
|
| 48. |
- Li, Wenxiang, et al.
(författare)
-
Facilities Collaboration in Cloud Manufacturing based on Generalized Collaboration Network
- 2015
-
Ingår i: Proceedings of the 11th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness. - : IEEE. - 9781631900631 ; , s. 298-303
-
Konferensbidrag (refereegranskat)abstract
- In cloud manufacturing for regional industrial cluster, there is increasing necessity of collaboration among enterprises or facilities. It is valuable to explore the characteristics of these collaboration behaviors for effectively scheduling dispersed manufacturing facilities and organizing their collaboration. The collaborative relation of manufacturing in regional industrial cluster can be described as a generalized social collaboration network. In this paper, we introduce the relevant entities and relations of facilities collaboration, and propose the method for building Facility Collaboration Network (FCN). We further design the dynamically growing process of FCN for different facility selection strategies, including random selection, balanced selection, random selection with preference and balanced selection with preference. Based on the metrics such as network scale, node degree distribution, act degree distribution, average shortest distance and number of cliques, we present the statistical characteristics of FCN, and analyze relevant characteristics and laws for efficient facilities selection in cloud manufacturing.
|
|
| 49. |
|
|
| 50. |
|
|
