bymavis's repositories
Adv_Weight_NeurIPS2021
The official code (PyTorch version) for paper 'Clustering Effect of Adversarial Robust Models'. (accepted by NeurIPS 2021, Spotlight)
3-Phish-Page-Detection
A machine learning based phishing detection prototype
bymavis.github.io
My homepage's source code
CodeT5
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.
CodeXGLUE
CodeXGLUE
ColossalAI
Making big AI models cheaper, easier, and more scalable
devign
Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
neural-anisotropy-directions
Source code for "Neural Anisotropy Directions"
ODGen
ODGen is a tool to detect multiple types of vulnerabilities in Node.js packages.
oldversion_joern
deepwukkong_preprocess
PhishingBaseline
Implementations of 3 phishing detection and identification baselines
PhishIntention
PhishIntention: Phishing detection through webpage intention
Phishpedia
Official Implementation of "Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages" USENIX'21
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
stealing-part-of-an-LM
An unofficial implementation of "Stealing Part of a Production Language Model"
Untargeted_Backdoor_Watermark
This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection', accepted in NeurIPS 2022.