arXiv subjects

Can Lu

Publications and source records attributed to Can Lu.

3 recordsLinked to original sources

arXiv2026

Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective

Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink adversarial transferability from a compact subspace perspective and propose CoSA, a transferable attack framework that operates within a shared low-dimensional semantic space. Specifically, each point cloud is represented as a compact combination of class-specific prototypes that capture shared semantic structure, while adversarial perturbations are optimized within a low-rank subspace to induce coherent and architecture-agnostic variations. This design suppresses model-dependent noise and constrains perturbations to semantically meaningful directions, thereby improving cross-model transferability without relying on surrogate-specific artifacts. Extensive experiments on multiple datasets and network architectures demonstrate that CoSA consistently outperforms state-of-the-art transferable attacks, while maintaining competitive imperceptibility and robustness under common defense strategies. Codes will be made public upon paper acceptance.

cs.CV↗

arXiv2019

Graph Iso/Auto-morphism: A Divide-&-Conquer Approach

The graph isomorphism is to determine whether two graphs are isomorphic. A closely related problem is automorphism detection, where an isomorphism between two graphs is a bijection between their vertex sets that preserves adjacency, and an automorphism is an isomorphism from a graph to itself. Applications of graph isomorphism/automorphism include database indexing, network simplification, network anonymization. By graph automorphism, we deal with symmetric subgraph matching (SSM), which is to find all subgraphs that are symmetric to a given subgraph in G. An application of SSM is to identify multiple seed sets that have the same influence power as a seed set found by influence maximization in a social network. To test two graphs for isomorphism, canonical labeling has been studied to relabel a graph in such a way that isomorphic graphs are identical after relabeling. Efficient canonical labeling algorithms have been designed by individualization-refinement. They enumerate all permutations using a search tree, and select the minimum as the canonical labeling, which prunes candidates during enumeration. Despite high performance in benchmark graphs, these algorithms face difficulties in handling massive graphs. In this paper, we design a new efficient canonical labeling algorithm DviCL. Different from previous algorithms, we take a divide-&-conquer approach to partition G. By partitioning G, an AutoTree is constructed, which preserves symmetric structures and the automorphism group of G. The canonical labeling for a tree node can be obtained by the canonical labeling of its child nodes, and the canonical labeling for the root is the one for G. Such AutoTree can also be effectively used to answer the automorphism group, symmetric subgraphs. We conducted extensive performance studies using 22 large graphs, and confirmed that DviCL is much more efficient and robust than the state-of-the-art.

cs.SI↗

arXiv2015

Exploring Hierarchies in Online Social Networks

Social hierarchy (i.e., pyramid structure of societies) is a fundamental concept in sociology and social network analysis. The importance of social hierarchy in a social network is that the topological structure of the social hierarchy is essential in both shaping the nature of social interactions between individuals and unfolding the structure of the social networks. The social hierarchy found in a social network can be utilized to improve the accuracy of link prediction, provide better query results, rank web pages, and study information flow and spread in complex networks. In this paper, we model a social network as a directed graph G, and consider the social hierarchy as DAG (directed acyclic graph) of G, denoted as GD. By DAG, all the vertices in G can be partitioned into different levels, the vertices at the same level represent a disjoint group in the social hierarchy, and all the edges in DAG follow one direction. The main issue we study in this paper is how to find DAG GD in G. The approach we take is to find GD by removing all possible cycles from G such that G = U(G) + GD where U(G) is a maximum Eulerian subgraph which contains all possible cycles. We give the reasons for doing so, investigate the properties of GD found, and discuss the applications. In addition, we develop a novel two-phase algorithm, called Greedy-&-Refine, which greedily computes an Eulerian subgraph and then refines this greedy solution to find the maximum Eulerian subgraph. We give a bound between the greedy solution and the optimal. The quality of our greedy approach is high. We conduct comprehensive experimental studies over 14 real-world datasets. The results show that our algorithms are at least two orders of magnitude faster than the baseline algorithm.

cs.SI↗