Thai Le's Projects
Thai Le, Noseong Park, Dongwon Lee. A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks. 59th Annual Meeting of the Association for Computational Linguistics (ACL) 2021.
Generate adversarial text via gradient methods
Adversarial Active Learning for Deep Networks
Code for the Noise Learning Adversarial Defense and PC analysis for adversary visualization
Source code for the paper "Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning." (Web Conference 2022)
A robust Python tool for text-based AI training and generation using GPT-2.
Interpretability and explainability of data and machine learning models
The Albacore Clickbait Detector
Download AudioSet for Vision-Audio-Text Pre-training
A collection of research materials on explainable AI/ML
This repository contains recent research on fake news.
This repository contains recent research on uncertainty estimation. Inspired from other 'awesome' github pages like awesome-deep-learning.
A curated list of backdoor learning resources
Crawling Articles from Buzzfeed Website
Implementation of CAPS: Comprehensible Abstract Policy Summaries
Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)
Reproducing Hu, et. al., ICML 2017's "Toward Controlled Generation of Text"
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
A pytorch adversarial library for attack and defense methods on images and graphs
DetectGPT code but for prediction on a single document. All credits go to **https://github.com/eric-mitchell/detect-gpt**
Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"
Code and website for DAL (Discriminative Active Learning) - a new active learning algorithm for neural networks in the batch setting.
Deep Q-learning (DQN) for Multi-agent Reinforcement Learning (RL)
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models