floatingmoonlight Goto Github PK

backdoor-learning-resources

A curated list of backdoor learning resources

ciku

ember-classification

extra-trees

Extremely Randomized Trees algorithm implementation in Python

gym-malware

helib

An Implementation of homomorphic encryption

k-nn-classification-algorithm

In this project, I will implement the k-NN classification algorithm and test it on the Iris dataset. k-NN classification method have two input parameters: Number of Neighbors(k), Distance Metric(Euclidean or Manhattan distance) Iris dataset contains three flowers and each flower is represented by four features: 1=sepal length, 2=sepal width, 3=petal length, and 4=petal width. In this assignment, I used the first and the fourth feature dimensions. I put first 30 samples from each flower class into the training set 20 samples into the test set. I organize iris data and change iris names with 0,1,2. Then I estimate distances between test set and training set and find minimum distances as k number and find its index to find which samples are closest. Then I find iris names and estimate accuracy rate.

keras_pruning

A walkthrough of how to prune keras models, using both weight-pruning and unit/neuron-pruning.

lfme

Code for "Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification", ECCV 2020 Spotlight

live-trojans

Code for "Live Trojan Attacks on Deep Neural Networks" paper

machinelearning

My blogs and code for machine learning. http://cnblogs.com/pinard

mediacrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫

mediacrawler_fork

Forked from NanmiCoder/MediaCrawler

np_ml

A tool library of classical machine learning algorithms with only numpy.

programming-language-qa

C/C++/Java/Python 基础知识总结

secml_malware

Create adversarial attacks against machine learning Windows malware detectors

simpleemailspoofer

A simple Python CLI to spoof emails.

spl

threat-hunting-malware-analysis-incident-response

Some portable tools, some YARA, some Python, and a little bit of love. Not all of these tools can be used in incident response. Use PEs with caution.