Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

AdvDoor: Adversarial Backdoor Attack of Deep Learning System

Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"

Code for "Label-Consistent Backdoor Attacks"

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…

An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

COMBAT: Alternated Training for Effective Clean-Label Backdoor Attack (AAAI 2024)

Large Language Model-enhanced Recommender System Papers

A Poetry Creation Platform Based on Visual Encoding and Natural Language Generation

Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)

Implementing Siamese networks with a contrastive loss for similarity learning

Visualizer for neural network, deep learning and machine learning models

Simplified Implementation of FedPAC

View model summaries in PyTorch!

Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)

Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"

A list of backdoor learning resources

My Personal Page

Virtual whiteboard for sketching hand-drawn like diagrams

ML models and internal tensors 3D visualizer

[ICLR2024]"Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency" by Soumyadeep Pal, Yuguang Yao, Ren Wang, Bingquan Shen, Sijia Liu

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning mode…

Code base for the NDSS24 paper Transpose Attack: Stealing Datasets with Bidirectional Training

Enhance Your English Writing for Science Research 写论文英语素材

本人的科研经验