perseuslee's repositories
TrustGuard
Source code of paper "TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support"
Kats-tutorials
Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.
DySAT_pytorch
Pytorch implementation of DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks
industry-analysis
Multi-variate time series forecasting using ML algorithms
deep-learning-and-rare-event-prediction
Deep Learning and Rare Event Prediction
Study-Notes-on-Time-Series
My study notes on time series. Will keep updating.
time-series-analysis--ARIMA
A study journal of time series analysis: ARIMA algorithm. With market sales dataset practice.
LSTM-Recurrent-Neural-Network
A deep learning project: RNN and its implementation in anomoly detection
INFOCOM2020-Guardian
Official code for the INFOCOM 2020 paper "Guardian: Evaluating Trust in Online Social Networks with Graph Convolutional Networks."
CNNInPytorch
一个PyTorch搭建CNN的中文基础教程
malicious-traffic-detection-classification
The continuing increase of Internet of Things (IoT) based networks have increased the need for Computer networks intrusion detection systems (IDSs). Over the last few years, IDSs for IoT networks have been increasing reliant on machine learning (ML) techniques, algorithms, and models as traditional cybersecurity approaches become less viable for IoT. IDSs that have developed and implemented using machine learning approaches are effective, and accurate in detecting networks attacks with high-performance capabilities. However, the acceptability and trust of these systems may have been hindered due to many of the ML implementations being ‘black boxes’ where human interpretability, transparency, explainability, and logic in prediction outputs is significantly unavailable. The UNSW-NB15 is an IoT-based network traffic data set with classifying normal activities and malicious attack behaviors. Using this dataset, three ML classifiers: Decision Trees, Multi-Layer Perceptrons, and XGBoost, were trained. The ML classifiers and corresponding algorithm for developing a network forensic system based on network flow identifiers and features that can track suspicious activities of botnets proved to be very high-performing based on model performance accuracies. Thereafter, established Explainable AI (XAI) techniques using Scikit-Learn, LIME, ELI5, and SHAP libraries allowed for visualizations of the decision-making frameworks for the three classifiers to increase explainability in classification prediction. The results determined XAI is both feasible and viable as cybersecurity experts and professionals have much to gain with the implementation of traditional ML systems paired with Explainable AI (XAI) techniques.
traffic_Graph_Convolutional_LSTM
Traffic Graph Convolutional Recurrent Neural Network
Stacked_Bidirectional_Unidirectional_LSTM
Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network
detect-lstm-model
检测恶意 URL and Request (Bi-LSTM、Bi-LSTM + CNN、CNN + Bi-LSTM、CNN + Bi-LSTM + CNN)
Attention_Network_With_Keras
An example attention network with simple dataset.
privacy
Library for training machine learning models with privacy for training data
awesome-machine-learning
A curated list of awesome Machine Learning frameworks, libraries and software.
Mynote
用于存放学习笔记
xxx
尝试
PrivateMultiplicativeWeights.jl
Differentially private synthetic data
Neural-Networks-for-time-series-analysis
Compare how ANNs, RNNs, LSTMs, and LSTMs with attention perform on time-series analysis
SPRINT_gan
Privacy-preserving generative deep neural networks support clinical data sharing
rappor
RAPPOR: Privacy-Preserving Reporting Algorithms
diffpriv
Easy differential privacy in R