Yuhao Zhang's repositories
defend_framework
This repository contains the implementation and evaluation of our Neurips 2022 paper: BagFlip: A Certified Defense Against Data Poisoning.
certified_lstms
This repository contains the implementation and evaluation of our EMNLP 2021 paper: Certified Robustness to Programmable Transformations in LSTMs.
academicpages.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
alpha-beta-CROWN
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021 and 2022)
auto_LiRPA
auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs
ccf-deadlines
⏰ CCF recommendation conference Deadline Countdowns / Please star this project, thanks~
closure-compiler
A JavaScript checker and optimizer.
ContraCLM
[ACL 2023] Code for ContraCLM: Contrastive Learning For Causal Language Model
convex_adversarial
A method for training neural networks that are provably robust to adversarial attacks.
docs
TensorFlow documentation
human-eval
Code for the paper "Evaluating Large Language Models Trained on Code"
MalwareBackdoors
Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers
POPQORN
An Algorithm to Quantify Robustness of Recurrent Neural Networks
RANUM
[ICSE 2023] Differentiable interpretation and failure-inducing input generation for neural network numerical bugs.
Structure-free-certified-NLP
SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)