Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)

Code for the paper: Label-Only Membership Inference Attacks

Algorithms to recover input data from their gradient signal through a neural network

[NeurIPS 2019] Deep Leakage From Gradients

Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)

Instance-wise Batch Label Restoration via Gradients In Federated Learning (ICLR 2023)

This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection', accepted in NeurIPS 2022.

Breaching privacy in federated learning scenarios for vision and text

[arXiv:2411.10023] "Model Inversion Attacks: A Survey of Approaches and Countermeasures"

Code for "Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment" (CCS 2019)

A code implementation for model inversion attack

[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks

LAMP: Extracting Text from Gradients with Language Model Priors (NeurIPS '22)

Query-Efficient Data-Free Learning from Black-Box Models

[IJCAI-2021] Contrastive Model Inversion for Data-Free Knowledge Distillation

A Pytorch implementation of "Data-Free Learning of Student Networks" (ICCV 2019).

python library for invisible image watermark (blind image watermark)