A list of awesome papers and cool resources on the topoc about adversarial sample on graph data. This list is focused on date data poisoning and defencing on Graph Convolutional Networks (GCNs) and Graph Neural Networks (GNNs). Please don't hesitate to suggest resources in other subfields of this topic.
Adversarial Attack and Defense on Graph Data: A Survey.
Adversarial Attacks on Graph Neural Networks via Meta Learning. 
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks.
Adversarial Personalized Ranking for Recommendation.
Adversarial Attack on Graph Structured Data.
Adversarial Attacks on Neural Networks for Graph Data.
Adversarially Trained Model Compression: When Robustness Meets Efficiency
Adversarial Attacks on Node Embeddings
Fast Gradient Attack on Network Embedding
Link Prediction Adversarial Attack
Attack Graph Convolutional Networks by Adding Fake Nodes
Data Poisoning Attack against Unsupervised Node Embedding Methods
Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications
Adversarial Network Embedding
Adversarial Recommendation: Attack of the Learned Fake Users
Attacking Similarity-Based Link Prediction in Social Networks
GA Based Q-Attack on Community Detection
Attend and Attack: Attention Guided Adversarial Attacks on Visual Question Answering Models
Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning
TODO
TODO
TODO
TODO