A comprehensive list of gradient inversion attacks in federated learning.

[NIPS25] Paper2Video: Automatic Video Generation from Scientific Papers

This is a collection of research papers for Federated Learning for Large Language Models (FedLLM). And the repository will be continuously updated to track the frontier of FedLLM.

YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception

A curated list of latest advances on Large Foundation Models with Federated Learning

TKDD2024-BapFL: You can Backdoor Attack Personalized Federated Learning

[CVPR 2025] Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

[ICLR 2024 ] Joint Local and Generic Federated Learning under Long-tailed Data

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

ICLR2024-Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

[CVPR 2024] Desigen: A Pipeline for Controllable Design Template Generation

开放式视觉故事生成模型 [CVPR 2024] Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

大世界模型

[CVPR 2024] Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions

针对ViT的对抗迁移性 TransferAttack [ICLR 2022] On Improving Adversarial Transferability of Vision Transformers

GradAttack [NIPS 2021] Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

图像和文本隐私泄露 Breaching privacy in federated learning scenarios for vision and text

多种后门攻击和防御集成 BackdoorBench

越狱攻击 EasyJailbreak

首篇扩散模型综述 [ACM Computing Surveys 2023] Diffusion model papers, survey, and taxonomy

模型劫持攻击 [Usenix Security 2024] Hijacking Attacks against Neural Network by Analyzing Training Data

AAAI2024 A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

TrojanZoo A universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

扩散模型 [AAAI 2024] Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model

异常检测 扩散模型 [AAAI 2024] DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection.

扩散模型. [CVPR 2022] LDM High-Resolution Image Synthesis with Latent Diffusion Models

持久性后门 [ICML 2023] Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning

隐私保护 [AAAI 2024] PPIDSG: A Privacy-Preserving Image Distribution Sharing Scheme with GAN in Federated Learning.

自条件图像生成. [arXiv 2312] 何恺明 Self-conditioned Image Generation via Generating Representations PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

图像掩码建模MIM. [CVPR 2023] Official repository for paper "Stare at What You See: Masked Image Modeling without Reconstruction"