Project Title: Building Structural Resistance to Adversarial Attacks in Convolutional Neural Networks
BASIS Advisor: Mr. Ingels
My Posts
Week Ten: Saturated Autoencoders
Hello everyone! This last week I have worked on creating a custom loss function to create a saturated denoising autoencoder. This works by adding a Regularizer to the loss function. In a traditional neural network, variables called weights are initially set to random values, and over the course of training, these weights are moved incrementally […]
Week Nine: Analysis and More Experimentation
Hello everyone! This last week I have done some thinking about the results of last week’s experiment and continued doing various small tests. In week eight I created a graph that shows how neural networks end up with high confidence in far-out regions of the input space. Interestingly I did not see any adversarial subspaces […]
Week Eight: 2D representation
Hello everyone! I have spent this last week creating a 2D representation of the Mnist dataset of handwritten digits and used that to create models of how neural networks classify space. I did this by training a new autoencoder with a latent dimension of 2 meaning it would learn to compress these images into 2 […]
Week Seven: Writing and Experiment Planning
Hello everyone! I spent this last week focusing on writing an introduction to my paper and on planning some experiments to do over the course of the next two weeks. Reading papers on saturated autoencoders and how they tend to be more overfitted to the data has piqued my interest in adversarial subspaces. As theory […]
Week Six: Learning More Math
Hello everyone! I have spent this past week taking some time to get back into my project after focusing on my fluid simulator project last week. To do this, I have spent the week teaching myself topics in linear algebra. I have learned about matrixes, the determinant, identity matrixes, unitary and orthogonal matrixes, Kronecker’s delta, […]
Week Five: AP Computer Science Principals Create Performance Task
Hello everyone! This last week I have not gotten too much time to dedicate to my senior project because I had to focus on my Create Performance Task for the AP Computer Science Principals exam. For this, I have to create a coding project that demonstrates my understanding of the principles behind computer science. I […]
Week Four: Saturating Autoencoders
Hello everyone! This last week I have worked on saturating the autoencoder I created in week 1. To do this I used the jacobian matrix based approach that I discussed in week 3. While planning to saturate my network, I created two objectives: to create resistance to small perturbations, and to not hurt the ability […]
Week Three: Saturating Networks
Hello everyone! I have spent this last week focusing on reading about saturating networks and studying more advanced topics in linear algebra. Saturating a network is the practice of making all the weight values on the more extreme ends, meaning they are either pretty big or pretty small with little in between. This is a […]
Week Two: Generating Adversarial Attacks
Hello everyone! I spent most of the week reading up on adversarial attacks and creating functions to produce them. One of the adversarial attack methods I replicated is the Fast Gradient Sign Method (FSGM) which takes the sign of an image’s gradient with respect to the loss function and multiplies that by some E which […]
Week One: Creating Resources
Hello everyone! This last week I have spent my time creating the setup for my project. This involved creating and training two different networks. The first of which is an autoencoder network that uses the MNIST dataset(a large dataset of handwritten digits). An autoencoder is a network that gets an image as input and then […]
Week Zero: An Introduction
Hello, my name is Szymon and I will be researching the use of non-linear networks alongside traditional convolutional layers to create structural resistance to adversarial attacks. You can learn more about what adversarial attacks are here, and you can read more about my project here. Thank you for reading!