| 1. |
- 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.
|
|
| 2. |
|
|
| 3. |
- Liu, Sheng, et al.
(författare)
-
FedRC : representational consistency guided model uploading mechanism for asynchronous federated learning
- 2023
-
Ingår i: Mobile and Ubiquitous Systems. - : Springer Nature. ; , s. 239-256
-
Konferensbidrag (refereegranskat)abstract
- Recently, a novel distributed machine learning paradigm called Federated learning (FL) has caught the eyes of both academics and industries, as it can orchestrate substantial Internet of Things (IoT) devices as clients to learn a global model collaboratively and efficiently without sharing sensitive data. Moreover, while comparing the two modes of FL, i.e., synchronous FL (SFL) and asynchronous FL (AFL), AFL is more scalable and flexible to address the issue of over-fitting and the performance bottleneck caused by the stragglers. However, the data heterogeneity and high communication consumption issues faced by AFL still hamper its further applications and deployments in ubiquitous IoT. Motivated by this, we propose FedRC, a model uploading mechanism for AFL, guided by Representational Consistency (RC). As a layer-wise uploading method for Deep Neural Networks (DNNs), FedRC calculates simplified Representational Dissimilarity Vectors (RDVs) for each local layer and corresponding global layer, respectively, after the local training of each client, and then measures RCs based on the two RDVs to adaptively determine the uploading of model layers. According to the evaluation based on three standard datasets, compared with four state-of-the-art baselines (i.e., FedAvg, FedProx, FedAsync, and PartialNet), FedRC can boost model accuracy by 3.48%, save communication costs by 26.79%, and shorten transmission time by 44.14%, respectively.
|
|
| 4. |
- Qu, Haohao, et al.
(författare)
-
Adaptation and Learning to Learn (ALL): An Integrated Approach for Small-Sample Parking Occupancy Prediction
- 2022
-
Ingår i: Mathematics. - : MDPI AG. - 2227-7390. ; 10:12, s. 2039-2039
-
Tidskriftsartikel (refereegranskat)abstract
- Parking occupancy prediction (POP) plays a vital role in many parking-related smart services for better parking management. However, an issue hinders its mass deployment: many parking facilities cannot collect enough data to feed data-hungry machine learning models. To tackle the challenges in small-sample POP, we propose an approach named Adaptation and Learning to Learn (ALL) by adopting the capability of advanced deep learning and federated learning. ALL integrates two novel ideas: (1) Adaptation: by leveraging the Asynchronous Advantage Actor-Critic (A3C) reinforcement learning technique, an auto-selector module is implemented, which can group and select data-scarce parks automatically as supporting sources to enable the knowledge adaptation in model training; and (2) Learning to learn: by applying federated meta-learning on selected supporting sources, a meta-learner module is designed, which can train a high-performance local prediction model in a collaborative and privacy-preserving manner. Results of an evaluation with 42 parking lots in two Chinese cities (Shenzhen and Guangzhou) show that, compared to state-of-the-art baselines: (1) the auto-selector can reduce the model variance by about 17.8%; (2) the meta-learner can train a converged model 102× faster; and (3) finally, ALL can boost the forecasting performance by about 29.8%. Through the integration of advanced machine learning methods, i.e., reinforcement learning, meta-learning, and federated learning, the proposed approach ALL represents a significant step forward in solving small-sample issues in parking occupancy prediction.
|
|
