flame0409
Focus on machine learning, deep learning, software engineering and big data security
Southwest University,ChinaChongqing,China
Pinned Repositories
adversarial_examples
对抗样本
Android
基于opcode的N-gram安卓恶意软件检测,主要代码,完整代码请见Android_Malware_detection,有疑问请联系flameguocp@163.com
android-malware
Collection of android malware samples
Android-Malware-Detection
使用安卓Opcode字节码的N-gram序列特征进行恶意软件检测的完全步骤,使用算法RF,KNN
Android_ClassLoader
联手项目:
Android_Malware_Detection-Adversarial-attack
实现了通过Android软件的Opcode的N-gram序列作为特征,在提取N-gram序列频率后,转化为7*7*7矩阵放入VGG-Net进行分类,并使用DeepFool进行对抗样本生成以及强化训练
awesome-vmp
虚拟化保护(VMP壳)分析相关资料
awesome_deep_learning_interpretability
深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)
DNN_Classcify
手撕代码,以tensorflow为基础框架,实现主要包括2分类及多分类ANN,CNN,InceptionNet,RES-net,VGG-Net等
Jane-Street-Market-Prediction
Your challenge will be to use the historical data, mathematical tools, and technological tools at your disposal to create a model that gets as close to certainty as possible. You will be presented with a number of potential trading opportunities, which your model must choose whether to accept or reject. In general, if one is able to generate a highly predictive model which selects the right trades to execute, they would also be playing an important role in sending the market signals that push prices closer to “fair” values. That is, a better model will mean the market will be more efficient going forward. However, developing good models will be challenging for many reasons, including a very low signal-to-noise ratio, potential redundancy, strong feature correlation, and difficulty of coming up with a proper mathematical formulation.
flame0409's Repositories
flame0409/Android-Malware-Detection
使用安卓Opcode字节码的N-gram序列特征进行恶意软件检测的完全步骤,使用算法RF,KNN
flame0409/Android
基于opcode的N-gram安卓恶意软件检测,主要代码,完整代码请见Android_Malware_detection,有疑问请联系flameguocp@163.com
flame0409/Android_Malware_Detection-Adversarial-attack
实现了通过Android软件的Opcode的N-gram序列作为特征,在提取N-gram序列频率后,转化为7*7*7矩阵放入VGG-Net进行分类,并使用DeepFool进行对抗样本生成以及强化训练
flame0409/Jane-Street-Market-Prediction
Your challenge will be to use the historical data, mathematical tools, and technological tools at your disposal to create a model that gets as close to certainty as possible. You will be presented with a number of potential trading opportunities, which your model must choose whether to accept or reject. In general, if one is able to generate a highly predictive model which selects the right trades to execute, they would also be playing an important role in sending the market signals that push prices closer to “fair” values. That is, a better model will mean the market will be more efficient going forward. However, developing good models will be challenging for many reasons, including a very low signal-to-noise ratio, potential redundancy, strong feature correlation, and difficulty of coming up with a proper mathematical formulation.
flame0409/DNN_Classcify
手撕代码,以tensorflow为基础框架,实现主要包括2分类及多分类ANN,CNN,InceptionNet,RES-net,VGG-Net等
flame0409/adversarial_examples
对抗样本
flame0409/android-malware
Collection of android malware samples
flame0409/Android_ClassLoader
联手项目:
flame0409/awesome-vmp
虚拟化保护(VMP壳)分析相关资料
flame0409/awesome_deep_learning_interpretability
深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)
flame0409/Deep-Android-Malware-Detection
Code for Deep Android Malware Detection paper
flame0409/flame0409
flame0409/GNNPapers
Must-read papers on graph neural networks (GNN)
flame0409/LeetCode
LeetCode training && Share
flame0409/neural-networks-and-deep-learning
Code samples for my book "Neural Networks and Deep Learning"