Graph-Adversarial-Learning

Graph-Adversarial-Learning

图对抗学习攻防技术与研究进展综述

该项目是一个图对抗学习综合资源库,收录2017年至今的攻击、防御和鲁棒性认证相关论文。资源按字母、年份和会议分类,并提供代码实现汇总。内容涵盖图神经网络攻击方法、防御策略和稳定性研究,为图对抗学习研究提供重要参考。

图对抗学习图神经网络攻击方法防御策略论文综述Github开源项目

⚔🛡 Awesome Graph Adversarial Learning

<img src="https://img.shields.io/badge/Contributions-Welcome-278ea5" alt="Contrib"/> <img src="https://img.shields.io/badge/Number%20of%20Papers-416-FF6F00" alt="PaperNum"/>

<a class="toc" id="table-of-contents"></a>

<img width =500 height =300 src="imgs/wordcloud.png" >

This repository contains Attack-related papers, Defense-related papers, Robustness Certification papers, etc., ranging from 2017 to 2021. If you find this repo useful, please cite: A Survey of Adversarial Learning on Graph, arXiv'20, Link

@article{chen2020survey, title={A Survey of Adversarial Learning on Graph}, author={Chen, Liang and Li, Jintang and Peng, Jiaying and Xie, Tao and Cao, Zengxu and Xu, Kun and He, Xiangnan and Zheng, Zibin and Wu, Bingzhe}, journal={arXiv preprint arXiv:2003.05730}, year={2020} }

👀Quick Look

The papers in this repo are categorized or sorted:

| By Alphabet | By Year | By Venue | Papers with Code |

If you want to get a quick look at the recently updated papers in the repository (in 30 days), you can refer to 📍this.

⚔Attack

2023

💨 Back to Top

2022

💨 Back to Top

  • Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem, 📝WSDM, :octocat:Code
  • Inference Attacks Against Graph Neural Networks, 📝USENIX Security, :octocat:Code
  • Model Stealing Attacks Against Inductive Graph Neural Networks, 📝IEEE Symposium on Security and Privacy, :octocat:Code
  • Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation, 📝WWW, :octocat:Code
  • Neighboring Backdoor Attacks on Graph Convolutional Network, 📝arXiv, :octocat:Code
  • Understanding and Improving Graph Injection Attack by Promoting Unnoticeability, 📝ICLR, :octocat:Code
  • Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs, 📝AAAI, :octocat:Code
  • More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks, 📝arXiv
  • Black-box Node Injection Attack for Graph Neural Networks, 📝arXiv, :octocat:Code
  • Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection, 📝arXiv
  • Projective Ranking-based GNN Evasion Attacks, 📝arXiv
  • GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation, 📝arXiv
  • Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization, 📝Asia CCS, :octocat:Code
  • Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees, 📝CVPR, :octocat:Code
  • Transferable Graph Backdoor Attack, 📝RAID, :octocat:Code
  • Adversarial Robustness of Graph-based Anomaly Detection, 📝arXiv
  • Label specificity attack: Change your label as I want, 📝IJIS
  • AdverSparse: An Adversarial Attack Framework for Deep Spatial-Temporal Graph Neural Networks, 📝ICASSP
  • Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks, 📝WSDM
  • Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors, 📝IJCAI, :octocat:Code
  • Label-Only Membership Inference Attack against Node-Level Graph Neural NetworksCluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors, 📝arXiv
  • Adversarial Camouflage for Node Injection Attack on Graphs, 📝arXiv
  • Are Gradients on Graph Structure Reliable in Gray-box Attacks?, 📝CIKM, :octocat:Code
  • Adversarial Camouflage for Node Injection Attack on Graphs, 📝arXiv
  • Graph Structural Attack by Perturbing Spectral Distance, 📝KDD
  • What Does the Gradient Tell When Attacking the Graph Structure, 📝arXiv
  • BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection, 📝ICDM, :octocat:Code
  • Model Inversion Attacks against Graph Neural Networks, 📝TKDE
  • Sparse Vicious Attacks on Graph Neural Networks, 📝arXiv, :octocat:Code
  • Poisoning GNN-based Recommender Systems with Generative Surrogate-based Attacks, 📝ACM TIS
  • Dealing with the unevenness: deeper insights in graph-based attack and defense, 📝Machine Learning
  • Membership Inference Attacks Against Robust Graph Neural Network, 📝CSS
  • Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks, 📝ICDM, :octocat:Code
  • Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective, 📝arXiv
  • Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection, 📝arXiv, :octocat:Code
  • Private Graph Extraction via Feature Explanations, 📝arXiv
  • Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Graphs, 📝arXiv
  • Camouflaged Poisoning Attack on Graph Neural Networks, 📝ICDM
  • LOKI: A Practical Data Poisoning Attack Framework against Next Item Recommendations, 📝TKDE
  • Adversarial for Social Privacy: A Poisoning Strategy to Degrade User Identity Linkage, 📝arXiv
  • Exploratory Adversarial Attacks on Graph Neural Networks for Semi-Supervised Node Classification, 📝Pattern Recognition
  • GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections, 📝arXiv, :octocat:Code
  • Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs, 📝arXiv
  • Are Defenses for Graph Neural Networks Robust?, 📝NeurIPS, :octocat:Code
  • Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation, 📝ECCV
  • Imperceptible Adversarial Attacks on Discrete-Time Dynamic Graph Models, 📝NeurIPS
  • Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias, 📝NeurIPS, :octocat:Code
  • Adversary for Social Good: Leveraging Attribute-Obfuscating Attack to Protect User Privacy on Social Networks, 📝SecureComm

2021

💨 Back to Top

编辑推荐精选

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

Qwen2.5-VL

Qwen2.5-VL

一款强大的视觉语言模型,支持图像和视频输入

Qwen2.5-VL 是一款强大的视觉语言模型,支持图像和视频输入,可用于多种场景,如商品特点总结、图像文字识别等。项目提供了 OpenAI API 服务、Web UI 示例等部署方式,还包含了视觉处理工具,有助于开发者快速集成和使用,提升工作效率。

HunyuanVideo

HunyuanVideo

HunyuanVideo 是一个可基于文本生成高质量图像和视频的项目。

HunyuanVideo 是一个专注于文本到图像及视频生成的项目。它具备强大的视频生成能力,支持多种分辨率和视频长度选择,能根据用户输入的文本生成逼真的图像和视频。使用先进的技术架构和算法,可灵活调整生成参数,满足不同场景的需求,是文本生成图像视频领域的优质工具。

WebUI for Browser Use

WebUI for Browser Use

一个基于 Gradio 构建的 WebUI,支持与浏览器智能体进行便捷交互。

WebUI for Browser Use 是一个强大的项目,它集成了多种大型语言模型,支持自定义浏览器使用,具备持久化浏览器会话等功能。用户可以通过简洁友好的界面轻松控制浏览器智能体完成各类任务,无论是数据提取、网页导航还是表单填写等操作都能高效实现,有利于提高工作效率和获取信息的便捷性。该项目适合开发者、研究人员以及需要自动化浏览器操作的人群使用,在 SEO 优化方面,其关键词涵盖浏览器使用、WebUI、大型语言模型集成等,有助于提高网页在搜索引擎中的曝光度。

xiaozhi-esp32

xiaozhi-esp32

基于 ESP32 的小智 AI 开发项目,支持多种网络连接与协议,实现语音交互等功能。

xiaozhi-esp32 是一个极具创新性的基于 ESP32 的开发项目,专注于人工智能语音交互领域。项目涵盖了丰富的功能,如网络连接、OTA 升级、设备激活等,同时支持多种语言。无论是开发爱好者还是专业开发者,都能借助该项目快速搭建起高效的 AI 语音交互系统,为智能设备开发提供强大助力。

olmocr

olmocr

一个用于 OCR 的项目,支持多种模型和服务器进行 PDF 到 Markdown 的转换,并提供测试和报告功能。

olmocr 是一个专注于光学字符识别(OCR)的 Python 项目,由 Allen Institute for Artificial Intelligence 开发。它支持多种模型和服务器,如 vllm、sglang、OpenAI 等,可将 PDF 文件的页面转换为 Markdown 格式。项目还提供了测试框架和 HTML 报告生成功能,方便用户对 OCR 结果进行评估和分析。适用于科研、文档处理等领域,有助于提高工作效率和准确性。

飞书多维表格

飞书多维表格

飞书多维表格 ×DeepSeek R1 满血版

飞书多维表格联合 DeepSeek R1 模型,提供 AI 自动化解决方案,支持批量写作、数据分析、跨模态处理等功能,适用于电商、短视频、影视创作等场景,提升企业生产力与创作效率。关键词:飞书多维表格、DeepSeek R1、AI 自动化、批量处理、企业协同工具。

下拉加载更多