Graphfool: Targeted Label Adversarial Attack on Graph Embedding

Adversarial Label Flips Attack on Support Vector Machines

To develop a robust classification algorithm in the adversarial setting, it is important to understand the adversary’s strategy. We address the problem of label flips attack where an adversary contaminates the training set through flipping labels. By analyzing the objective of the adversary, we formulate an optimization framework for finding the label flips that maximize the classification erro...

Adversarial Network Embedding

Learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization. Existing methods can effectively encode different structural properties into the representations, such as neighborhood connectivity patterns, global structural role similarities and other highorder proximities. However, except fo...

Graph grammars with node-label controlled rewriting and embedding

On Simultaneous Graph Embedding

We consider the problem of simultaneous embedding of planar graphs. There are two variants of this problem, one in which the mapping between the vertices of the two graphs is given and another where the mapping is not given. In particular, we show that without mapping, any number of outerplanar graphs can be embedded simultaneously on an O(n)×O(n) grid, and an outerplanar and general planar gra...

On-Line Planar Graph Embedding

We present a dynamic data structure for the incremental construction of a planar embedding of a planar graph. The data structure supports the following Ž . operations: i testing if a new edge can be added to the embedding without Ž . introducing crossing; and ii adding vertices and edges. The time complexity of Ž . Ž . each operation is O log n amortized for edge insertion , and the memory spac...