In the previous post, we talked about some of the attack vectors on the DNS. In this post, we're going to be talking about DNSSEC, which is an attempt to make the DNS more secure. A point to note, DNSSEC does not provide Confidentiality, but only Integrity. Integrity in this case is ensuring that the … Continue reading DNSSEC
Before looking at DNS Attack Vectors, let's do a quick recap of what a DNS is, and what are it's functions. What is a DNS? DNS, or Domain Name System, is a server that provides Name to IP Address resolution. When people visit websites, it's much easier for them to remember words, such as Facebook … Continue reading DNS Attack Vectors
In the previous post, we talked about RNN, and how performing Backpropagation through time (BPTT) on an unrolled RNN with many time steps can lead to the problems of vanishing / exploding gradients, and difficulties in learning long term dependencies. In this post, we're going to look at a the LSTM (Long Short Term Memory) … Continue reading LSTM
In this post, we're going to be looking at: Recurrent Neural Networks (RNN)Weight updates in an RNNUnrolling an RNNVanishing/Exploding Gradient Problem Recurrent Neural Networks A Recurrent Neural Network (RNN) is a variant of neural networks, where in each neuron, the outputs cycle back to themselves, hence being recurrent. Each neuron's output cycle back to themselves, … Continue reading RNN and Vanishing/Exploding Gradients
A Proxy, or a Proxy Server / Web Proxy, is something that sits between the source of the network traffic, and the desired destination of the traffic. What the proxy will do is relay the network traffic across to the other side. Typically, it would sit between a client and a server, where the client … Continue reading What are Proxies?
K-Means Clustering is an unsupervised learning algorithm. It works by grouping similar data points together to try to find underlying patterns. The number of groups are pre-defined by the user as K. How the Algorithm works Before the iterative update starts, a random selection of centroid locations are picked on the graph. These centroids act … Continue reading K-Means Clustering
Domain fronting is a malicious act of appearing to request to visit a legitimate site (the front), while in actual fact, the request is going to another website. Domain fronting relies on the SSL technology to work, where the service provider is unable to see the actual malicious hostname the request is going to, but … Continue reading Domain Fronting and SNI
A random forest is an ensemble approach of combining multiple decision trees. Ensembling and Decision Trees, we first need to explain what these two things are Decision Trees Decision Trees try to encode and separate the data into if-else rules. It breaks the data down into smaller and smaller subsets. Each node poses the question, … Continue reading Random Forests
Just finished reading the book "The Master Algorithm", where the author tries to find the ultimate Machine Learning algorithm that can solve different varieties of problems (text, image, predictive, time series etc) In the book, he goes over the 5 main branches (or tribes) of Machine Learning. They are: The EvoluntionariesThe ConnectionistThe SymbolistThe BayesiansThe Analogizers … Continue reading Branches of Machine Learning
A Generative Adversarial Network (GAN) is a collection of two neural network models: A Discriminator, and a Generator. The goals of the two models are opposing to each other Discriminator: Given a set of features, we try to predict the label Generator: Given a label, we try to predict the features that lead to the … Continue reading GAN?