bboylyg Goto Github PK

followers: 31.0 following: 9.0 repos: 26.0 gists: 0.0

Name: Yige-Li

Type: User

Bio: Postdoctoral Fellow, Singapore Management University

Location: Singapore

Hi there, I am Yige Li👋

I have completed my Ph.D. degree at Xidian University supervised by Prof. Xixiang Lyu. Research publications in Google Scholar.

🔭 My research mainly focus on:

Understanding the eﬀectiveness of backdoor attacks
Robust training against backdoor attacks
Design and implement a general defense framework for backdoor attacks

🌱 Publications:

Yige Li, Xingjun Ma, et al., “Multi-Trigger Backdoor Attacks: More Triggers, More Threats”, submitting, 2024.
Yige Li, Xixiang Lyu, et al., “Reconstructive Neuron Pruning for Backdoor Defense”, ICML 2023.
Yige Li, Xixiang Lyu, et al., “Anti-Backdoor Learning: Training Clean Models on Poisoned Data”, NeurIPS 2021.
Yige Li, Xixiang Lyu, et al., “Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks”, ICLR 2021.

⚡ Significance of our works:

Neural Attention Distillation (NAD)
- A simple and universal method against 6 state-of-the-art backdoor attacks via knowledge distillation
- Only a small amount of clean data is required (5%)
- Only a few epochs of fine-tuning (2-10 epochs) are required
Anti-Backdoor Learning (ABL)
- Simple, effective, and universal, can defend against 10 state-of-the-art backdoor attacks
- 1% isolation data is required
- A novel stratrgy benefit companies, research institutes, or government agencies to train backdoor-free machine learning models

📫 How to reach me:

[email protected]

Yige-Li's Projects

abl

Anti-Backdoor learning (NeurIPS 2021)

adversarial-robustness-toolbox

Python library for adversarial machine learning, attacks and defences for neural networks, logistic regression, decision trees, SVM, gradient boosted trees, Gaussian processes and more with multiple framework support

ai-security-for-iot-and-mobile

backdoors_in_ml_models

Research focused on identifying backdoor triggers in machine learning models and creating a noise filter as a suppression mechanism for the triggers.

bboylyg

book-resources

ensemble_cnn_models_for_classification

Ensemble_CNN _Models_For_Classification.

fewshotknowledgetransfer

KD+AT baselines for the paper "Zero-shot Knowledge Transfer via Adversarial Belief Matching"

freezeg

Freezing generator for pseudo image translation

hackingneuralnetworks

A small course on exploiting and defending neural networks

handson-ml2

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

human-activity-recognition

Recognizing human activities using Deep Learning

imagecorruptions

Corrupt arbitrary images.

keras-resources

Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library

machinelearning_python

机器学习算法python实现

ml-paper-notes

:notebook: Notes and summaries of various ML, Computer Vision & NLP papers.

nad

This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://openreview.net/pdf?id=9l0K4OM-oXE) in PyTorch.