Thai Le's repositories
shield-defend-adversarial-texts
Repository of the paper "SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher" accepted to ACL'22
perturbations-in-the-wild
Repository of the paper "Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense", ACL22 (Findings)
Adversarial_SocialBots_WWW22
Source code for the paper "Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning." (Web Conference 2022)
ACL2021-DARCY-HoneypotDefenseNLP
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.
synthetic_clickbait
[ASONAM 2019] Synthetic Texts (clickbaits) Generation using Different Variations of VAE. Code for paper "5 Sources of Clickbaits You Should Know! Using Synthetic Clickbaits to Improve Prediction and Distinguish between Bot-Generated and Human-Written Headlines"
audioset-dl
Download AudioSet for Vision-Audio-Text Pre-training
Awesome-explainable-AI
A collection of research materials on explainable AI/ML
certified-word-sub
Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)
CSrankings
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.
DetectGPT-Single
DetectGPT code but for prediction on a single document. All credits go to **https://github.com/eric-mitchell/detect-gpt**
facenet-pytorch
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
graph_sample_rl
Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling (official code repository)
lethaiq.github.io
Personal Website of Thai Le
Obfuscation-Detection
Obfuscation detection tool. Given a document, it tells if it has been written by human or altered by an automated authorship obfuscation tool.
OpenAttack
An Open-Source Package for Textual Adversarial Attack.
sbryngelson.github.io
Bryngelson research group website
TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
xai-iml-sota
Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
XAIFooler_EMNLP23
Source code for ``Are Your Explanations Reliable?" Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack