I implemented [Stanislav Fort's project](https://twitter.com/stanislavfort/status/1481263565998805002?s=20) in Pytorch. The Github repo has a notebook which looks at generating adversarial images to 'fool' the ConvNeXt model's image classification capabilities. ConvNeXt came out earlier this year (2022) from Meta AI. The FGSM (Fast Gradient Sign Method) is a great algorithm to attack models in a white-box fashion with the goal of misclassification. Noise is added to the input image (not randomly) but in a manner such that the direction is the same as the gradient of the cost function with respect to the data.
Implementations of some popular optimizers from scratch for a simple model i.e., Linear Regression on a dataset of 5 features. The goal of this project was to understand how these optimizers work under the hood and try to do a toy implementation myself. I also use a bit of JAX magic to perform the differentiation of the loss function w.r.t to the weights and the bias without explicitly writing their derivatives as a separate function. This can help to generalize this notebook for other types of loss functions as well.
After my last post on deploying Machine Learning and Deep Learning models using FastAPI and Docker, I wanted to explore a bit more on deploying deep learning models. My last post discussed a server-side method for deploying the model. This post will discuss client side frameworks and techniques to deploy those models such that they work directly on the client side.
In this tutorial I will be giving an overview of three frameworks, Tensorflow.
A study on fooling Machine Learning/Deep Learning based Network Intrusion Detection systems to prevent them from detecting intrusions
Implemented various papers on Linux Malware detection, where I analysed the structure of ELF files to determine whether they were malicious or benign. Approaches included the analysis of -
Symbol Table Opcode frequency ELF file metadata