graph-adversarial-learning-literature

graph-adversarial-learning-literature

图数据对抗攻防研究文献综述

该项目整理了图结构数据对抗攻击和防御相关论文,涵盖节点分类、图分类、链接预测等任务。论文按上传日期降序排列,便于了解最新进展。项目还包含一篇综述文章,回顾110多篇相关研究。对图对抗学习研究者提供了系统性的文献资源。

图对抗学习图神经网络攻击方法防御策略节点分类Github开源项目
<div align="center"> <h1>Awesome Graph Adversarial Learning Literature</h1> <a href="https://awesome.re"><img src="https://awesome.re/badge.svg"/></a> <a href="http://makeapullrequest.com"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square"/></a> </div>

A curated list of adversarial attacks and defenses papers on graph-structured data.

Papers are sorted by their uploaded dates in descending order.

If you want to add new entries, please make PRs with the same format.

This list serves as a complement to the survey below.

Adversarial Attack and Defense on Graph Data: A Survey (Updated in Oct 2022. More than 110 papers reviewed).

  • Arxiv Version (Latest)
@article{sun2018adversarial, title={Adversarial Attack and Defense on Graph Data: A Survey}, author={Sun, Lichao and Dou, Yingtong and Yang, Carl and Kai Zhang and Wang, Ji and Yixin Liu and Yu, Philip S. and He, Lifang and Li, Bo}, journal={arXiv preprint arXiv:1812.10528}, year={2018} }
  • TKDE Version
@article{sun2022adversarial, title={Adversarial attack and defense on graph data: A survey}, author={Sun, Lichao and Dou, Yingtong and Yang, Carl and Zhang, Kai and Wang, Ji and Philip, S Yu and He, Lifang and Li, Bo}, journal={IEEE Transactions on Knowledge and Data Engineering}, year={2022}, publisher={IEEE} }

If you feel this repo is helpful, please cite the survey above.

How to Search?

Search keywords like conference name (e.g., NeurIPS), task name (e.g., Link Prediction), model name (e.g., DeepWalk), or method name (e.g., Robust) over the webpage to quickly locate related papers.

Quick Links

Attack papers sorted by year: | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 |

Defense papers sorted by year: | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 |

Attack

Attack Papers 2023 [Back to Top]

YearTitleTypeTarget TaskTarget ModelVenuePaperCode
2023Revisiting Robustness in Graph Machine LearningAttackNode ClassificationGCN, SGC, APPNP, GAT, GATv2, GraphSAGE, LPICLR'23LinkLink
2023Unnoticeable Backdoor Attacks on Graph Neural NetworksAttackNode classification, Graph classificationGCN, GraphSage, and GATArXivLinkLink
2023Attacking Fake News Detectors via Manipulating News Social EngagementAttackFake News DetectionGAT, GCN, and GraphSAGE)WWW'23LinkLink
2023HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural NetworksAttackNode ClassificationHGNNsArXivLink
2023Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural NetworksAttackNode ClassificationGCNCVPR'23Link
2023Adversary for Social Good: Leveraging Attribute-Obfuscating Attack to Protect User Privacy on Social NetworksAttackAttribute Protection On Social NetworksGNNsSecureComm 2022Link
2023Node Injection for Class-specific Network PoisoningAttackNode ClassificationGCNarXivLinkLink
2023GUAP: Graph Universal Attack Through Adversarial PatchingAttackNode ClassificationGCNarXivLinkLink

Attack Papers 2022 [Back to Top]

YearTitleTypeTarget TaskTarget ModelVenuePaperCode
2022GANI: Global Attacks on Graph Neural Networks via Imperceptible Node InjectionsAttackNode ClassificationGCN/SGC/Jaccard/SimPGCNArxivLink
2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via MotifsAttackGraph ClassificationGCN/SAGPool/GIN/ArxivLink
2022Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient DebiasAttackNode ClassificationGCN/GAT/GraphSAGENeurIPS 2022LinkLink
2022Imperceptible Adversarial Attacks on Discrete-Time Dynamic Graph ModelsAttackDynamic Link Prediction/Node ClassificationGC-LSTM/EVOLVEGCN/DYSATNeurIPS 2022 Workshop TGLLink
2022A2S2-GNN: Rigging GNN-Based Social Status by Adversarial Attacks in Signed Social NetworksAttackClassification in unsigned or undirected graphsGNNsIEEE Transactions on Information Forensics and SecurityLink
2022Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement LearningAttackNode ClassificationGCN/SGC/GAT/APPNPAAAI23LinkLink
2022QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based SystemsAttackQuery-based systems attribute inferenceDiffix/TableBuilder/SimpleQBSCCS 2022LinkLink
2022Are Defenses for Graph Neural Networks Robust?AttackNode ClassificationGNN, GCN, Jaccard GCN, SVD GCN, GNNGuard, RGCN, ProGNN, GRAND, Soft Median GDCNeurIPS 2022LinkLink
2022Poisoning GNN-based Recommender Systems with Generative Surrogate-based AttacksAttackPromotion/Recommendation/Re-producingGNNACM TISLink
2022Dealing with the unevenness: deeper insights in graph-based attack and defenseAttackSet-Cover problemGCN, RGCN, GCN-Jaccard, Pro-GNNMachine LearningLink
2022Membership Inference Attacks Against Robust Graph Neural NetworkAttackMembership InferenceGCNCSS 2022Link
2022Sparse Vicious Attacks on Graph Neural NetworksAttackLink predictionGNNarXivLinkLink
2022Model Inversion Attacks against Graph Neural NetworksAttackNode ClassificationGCN, GAT and GraphSAGETKDELinkLink
2022Exploratory Adversarial Attacks on Graph Neural Networks for Semi-Supervised Node ClassificationAttackSemi-Supervised Node ClassificationGNNPattern RecognitionLink
2022Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural NetworksAttacknode classificationGNNIEEE ICDM 2022LinkLink
2022Resisting Graph Adversarial Attack via Cooperative Homophilous AugmentationAttacksemi-Supervised Node ClassificationGNNECML PKDD 2022Link
2022What Does the Gradient Tell When Attacking the Graph StructureAttackNode ClassificationGCN, GraphSage and H2GCNarXivLink
2022Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label PropagationAttackNode ClassificationGNNsCIKM 2022LinkLink
2022Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack PerspectiveAttackCollaborative filteringLightGCNarXivLink
2022Link-Backdoor: Backdoor Attack on Link Prediction via Node InjectionAttackLink PredictionGAE, VGAE, GIC, ARGA, ARVGAarXivLinkLink
2022Graph Structural Attack by Perturbing Spectral DistanceAttacknode classificationtwo-layer GCNKDD 2022Link
2022Are Gradients on Graph Structure Reliable in Gray-box Attacks?Attacknode classification tasksGraphSageCIKM 2022Link
2022Adversarial Camouflage for Node Injection Attack on GraphsAttacksemi-supervised information retrieval taskGNNsarXivLink
2022CLUSTER ATTACK: Query-based Adversarial Attacks on Graphs with Graph-Dependent PriorsAttacknode classificationGNNsIJCAI 2022Link
2022IoT-based Android Malware Detection Using Graph Neural Network With Adversarial DefenseAttackMalware DetectionGNNIEEE Internet of ThingsLink
2022Private Graph Extraction via Feature ExplanationsAttacknode classification2-layer GCNarXivLink
2022Towards Secrecy-Aware Attacks Against Trust Prediction in Signed GraphsAttacktrust prediction in signed graphsSGCN, SNEAarXivLink
2022Camouflaged Poisoning Attack on Graph Neural NetworksAttacknode classificationGCNICMR 2022Link
2022LOKI: A Practical Data Poisoning Attack Framework against Next Item RecommendationsAttackNext Item RecommendationsBPRMF, FPMC, GRU4REC, TransRecTKDE 2022Link
2022Poisoning GNN-based Recommender Systems with Generative Surrogate-based AttacksAttackPromotion/Recommendation/Re-producingGNNsACM Transactions on Information Systems 2022Link
2022Transferable Graph Backdoor AttackAttackGraph ClassificationGNNsRAID 2022Link
2022Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent PriorsAttackNode ClassificationGNNsIJCAI 2022LinkLink
2022Adversarial Robustness of Graph-based Anomaly DetectionAttackAnomaly DetectionGNNsArxivLink
2022Adversarial Attack Framework on Graph Embedding Models with Limited KnowledgeAttackNode ClassificationGNNsPreprint

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