Anshuman Suri's Projects
Code for A-LINK and A2-LINK
Fooling neural based speech recognition systems.
AI course assignments
Assignments done for Advanced Pattern Recognition and Machine Learning course (CSE640)
ARM Simulator
Targeted Adversarial Examples on Speech-to-Text systems
Proposed defenses against several adversarial attacks for speech to text systems
Code used for the blogpost 'Reassessing adversarial training with fixed data augmentation'
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
An awesome list of papers on distribution/property inference in machine learning
An awesome list of papers on privacy attacks against machine learning
A curated list of awesome Python frameworks, libraries, software and resources
Server and RPi code to send temperature readings to IoT hub from a Raspberry Pi
Some scripts to download atomic elements' data, parse it and store it in a database. (Part of proposal for GSoC '16)
Bidirectional Attention Flow
Code for 'SoK: Pitfalls in Evaluating Black-Box Attacks' , SaTML 2024.
A simple BLOSUM toolbox for python3
Blue Hexagon Open Dataset for Malware AnalysiS. Code for our DLS'21 paper - BODMAS: An Open Dataset for Learning based Temporal Analysis of PE Malware
Topological botnet detection datasets and graph neural network applications
BrainDump is a simple, powerful, and open note taking platfform that makes it easy to organize your life.
Website for reading group on Causal Learning, UVA (Summer 2023)
Assignments done for Collaborative Filtering course (CSE640)
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) : a robustness metric for deep neural networks
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Website for Computational Biology / Biological Computing Course
A project to analyze the impact of operating-system concepts on the efficiency of multi-threaded programs (CSE231 assignment)
code, data, and model for ACL-19 paper "Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading"