Yuwei Sun 교수

Wider coverage and a better solution to a latency reduction in 5G necessitate its combination with multi-access edge computing technology. Decentralized deep learning (DDL), such as federated learning and swarm learning, as a promising solution to privacy-preserving data processing for millions of smart edge devices leverages distributed computing of multilayer neural networks within the networking of local clients, without disclosing the original local training data. Notably, in industries such

Predominant network intrusion detection systems (NIDS) aim to identify malicious traffic patterns based on a handcrafted dataset of rules. Recently, the application of machine learning in NIDS helps alleviate the enormous effort of human observation. Federated learning (FL) is a collaborative learning scheme concerning distributed data. Instead of sharing raw data, it allows a participant to share only a trained local model. Despite the success of existing FL solutions, in NIDS, a network's traf

Traditional approaches to cybersecurity issues usually protect users from attacks after the occurrence of specific types of attacks. Besides, patterns of recent cyberattacks tend to be changeable, which add up to unpredictability of them. On the other hand, machine learning, as a new method used to detect intrusion, is attracting more and more attention. Moreover, through the sharing of local training data, the centralized learning approach has proven to improve a model's performance. In this re

Model poisoning attacks on federated learning intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired behaviors. In particular, we considered a semi-targeted situation where the source class is predetermined however the target class is not. The goal is to cause the global classifier to misclassify data of the source class. Though approaches such as label flipping ha

With the approach of 5G Society, more and more devices have been connected to the Internet, where information is stored, analyzed, and shared. Federated learning allows participants to train a machine learning model through sharing the parameters of it based on local training, instead of raw private data at local. In this research, we propose the implementation of the blockchain in federated learning for local parameters evaluation and global parameter aggregation, thus alleviating the influence

With increasingly more sophisticated phishing campaigns in recent years, phishing emails lure people using more legitimate-looking personal contexts. To tackle this problem, instead of traditional heuristics-based algorithms, more adaptive detection systems such as natural language processing (NLP)powered approaches are essential to understanding phishing text representations. Nevertheless, concerns surrounding the collection of phishing data that might cover confidential information hinder the

Federated learning (FL) has been facilitating privacy-preserving deep learning in many walks of life such as medical image classification, network intrusion detection, and so forth. Whereas it necessitates a central parameter server for model aggregation, which brings about delayed model communication and vulnerability to adversarial attacks. A fully decentralized architecture like Swarm Learning allows peer-to-peer communication among distributed nodes, without the central server. One of the mo

A survey paper.

Existing model poisoning attacks on federated learning (FL) assume that an adversary has access to the full data distribution. In reality, an adversary usually has limited prior knowledge about clients' data. A poorly chosen target class renders an attack less effective. This work considers a semi-targeted situation where the source class is predetermined but the target class is not. The goal is to cause the misclassification of the global classifier on data from the source class. Approaches suc

An attack on deep learning systems where intelligent machines collaborate to solve problems could cause a node in the network to make a mistake on a critical judgment. At the same time, the security and privacy concerns of AI have galvanized the attention of experts from multiple disciplines. In this research, we successfully mounted adversarial attacks on a federated learning (FL) environment using three different datasets. The attacks leveraged generative adversarial networks (GANs) to affect

The digitalization occurring in various industries is bringing more information transmitted through networks. More resilient and efficient network traffic monitoring systems are in high demand to safeguard network flows. In this article, we presented a combined approach of anomaly detection in LAN based on raw network traffic observation and measurement, the collected data being converted to regulated chunks of 480 bits. A network traffic dataset including multi-type anomalies from a honeypot de

Security of local area network (LAN) attracts many attentions in recent years. A malware delivered, for example by phishing e-mails, intrudes and expands into the other hosts in the LAN easily these days. Previous works have taken machine learning approach to detect anomaly caused by malware's behavior. However, there are still not so many researches that try to clarify the reasons of such anomaly, i.e., explanation of the anomaly causes. In this research, we propose a method using convolutional

Plant synthetic biology research requires diverse bioparts that facilitate the redesign and construction of new-to-nature biological devices or systems in plants. Limited by few well-characterized bioparts for plant chassis, the development of plant synthetic biology lags behind that of its microbial counterpart. Here, we constructed a web-based Plant Synthetic BioDatabase (PSBD), which currently categorizes 1677 catalytic bioparts and 384 regulatory elements and provides information on 309 spec

In this article, we presented a visualization method for representing network traffic features using raw data of it. The raw network traffic data was divided into regulated segments. By employing a supervised neural network and an expert-knowledge based labeling method, model training was conducted based on a dataset covering two weeks' network traffic, where the first week's data was employed as the training set and the second week's data was used as the validation set. At last, we achieved val

<p>Multi-source domain adaptation has been intensively studied. The distribution shift in features inherent to specific domains causes the negative transfer problem, degrading a model’s generality to unseen tasks. In Federated Learning (FL), learned model parameters are shared to train a global model that leverages the underlying knowledge across client models trained on separate data domains. Nonetheless, the data confidentiality of FL hinders the effectiveness of traditional domain adapt