Filters








378 Hits in 7.9 sec

Node Injection Attacks on Graphs via Reinforcement Learning [article]

Yiwei Sun, Suhang Wang, Xianfeng Tang, Tsung-Yu Hsieh, Vasant Honavar
2019 arXiv   pre-print
We describe a reinforcement learning based method, namely NIPA, to sequentially modify the adversarial information of the injected nodes.  ...  Previous work on graph adversarial attacks focus on modifying existing graph structures, which is infeasible in most real-world applications.  ...  Figure 2 : 2 An overview of the Proposed Framework NIPA for Node Injection Attack on Graphs information L A t with neural networks.  ... 
arXiv:1909.06543v1 fatcat:hy6roshhvvgwlez3eagsoa7z3y

Reinforcement Learning For Data Poisoning on Graph Neural Networks [article]

Jacob Dineen, A S M Ahsan-Ul Haque, Matthew Bielskas
2021 arXiv   pre-print
We will study the novel problem of Data Poisoning (training time) attack on Neural Networks for Graph Classification using Reinforcement Learning Agents.  ...  Since a Graph Classification dataset consists of discrete graphs with class labels, related work has forgone direct gradient optimization in favor of an indirect Reinforcement Learning approach.  ...  The first attack introduced by [16] is RL-S2V, a Hierarchical Reinforcement Learning (HRL) approach for both Node and Graph Classification at test-time.  ... 
arXiv:2102.06800v1 fatcat:xme7cul6wfdkpgre6efsu2q4hu

Reinforcement learning on graphs: A survey [article]

Nie Mingshuo, Chen Dongming, Wang Dongqi
2022 arXiv   pre-print
In this survey, we provide a comprehensive overview of RL and graph mining methods and generalize these methods to Graph Reinforcement Learning (GRL) as a unified formulation.  ...  As far as we know, this is the latest work on a comprehensive survey of GRL, this work provides a global view and a learning resource for scholars.  ...  REINFORCEMENT LEARNING ON GRAPHS Existing methods to solve graph data mining problems with RL methods focus on network representation learning, adversarial attacks, relational reasoning.  ... 
arXiv:2204.06127v2 fatcat:7wf6qxnxzza7xbiwjgjmrsrdjq

Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies [article]

Wei Jin, Yaxin Li, Han Xu, Yiqi Wang, Shuiwang Ji, Charu Aggarwal, Jiliang Tang
2020 arXiv   pre-print
As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability.  ...  Thus, it is necessary and timely to provide a comprehensive overview of existing graph adversarial attacks and the countermeasures.  ...  Adversarial attacks on graph neural networks via meta learning. arXiv preprint arXiv:1902.08412, 2019. [92] D. Zügner and S. Günnemann.  ... 
arXiv:2003.00653v3 fatcat:q26p26cvezfelgjtksmi3fxrtm

Graph Neural Networks: Taxonomy, Advances and Trends [article]

Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li, Jumin Zhao
2022 arXiv   pre-print
This survey aims to overcome this limitation, and provide a comprehensive review on the graph neural networks.  ...  However, they usually lay emphasis on different angles so that the readers can not see a panorama of the graph neural networks.  ...  PI and GNNs, adversarial attacks for the GNNs, graph neural architecture search and graph reinforcement learning.  ... 
arXiv:2012.08752v3 fatcat:xj2kambrabfj3g5ldenfyixzu4

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., +, TCYB May 2020 1900-1909 Hierarchical systems A Hierarchical Recurrent Neural Network for Symbolic Melody Generation.  ...  ., +, TCYB May 2020 1887-1899 Learning Optimized Structure of Neural Networks by Hidden Node Pruning With L 1 Regularization.  ...  Stock markets A Quantum-Inspired Similarity Measure for the Analysis of Complete Weighted Graphs. Bai, L., +, TCYB March 2020 1264 -1277  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

Attacking Black-box Recommendations via Copying Cross-domain User Profiles [article]

Wenqi Fan, Tyler Derr, Xiangyu Zhao, Yao Ma, Hui Liu, Jianping Wang, Jiliang Tang, Qing Li
2022 arXiv   pre-print
Thus, advanced injection attacks of creating more 'realistic' user profiles to promote a set of items is still a key challenge in the domain of deep learning based recommender systems.  ...  In this work, we present our framework CopyAttack, which is a reinforcement learning based black-box attack method that harnesses real users from a source domain by copying their profiles into the target  ...  Attacking Environment and Parameter Settings. Graph Neural Networks (GNNs) based techniques are the state-of-the-art models for recommender systems [19] .  ... 
arXiv:2005.08147v2 fatcat:s25ta4ulrza3zcb6na56nagony

Models and Framework for Adversarial Attacks on Complex Adaptive Systems [article]

Vahid Behzadan, Arslan Munir
2017 arXiv   pre-print
Building on this foundation, we propose a framework based on reinforcement learning for simulation and analysis of attacks on CAS, and demonstrate its performance through three real-world case studies  ...  We introduce the paradigm of adversarial attacks that target the dynamics of Complex Adaptive Systems (CAS).  ...  The case of sequential attacks on power grids is recently studied by Yan et al. [48] , who also use a an approach based reinforcement learning to analyze the impact of such attacks.  ... 
arXiv:1709.04137v1 fatcat:risynvwcrffbddmogtwg5cmcli

Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks [article]

Zihan Liu, Yun Luo, Zelin Zang, Stan Z. Li
2021 arXiv   pre-print
This paper investigates the effect of representation learning of surrogate models on the transferability of gray-box graph adversarial attacks.  ...  The general node classification model loses the topology of the nodes on the graph, which is, in fact, an exploitable prior for the attacker.  ...  Some related articles [18, 19] have also proposed to enhance node injection attack models based on reinforcement learning. Zinger et al.  ... 
arXiv:2110.10482v2 fatcat:jn2sgba2ozfdre5ohg566epd5a

A Survey on Adversarial Attacks for Malware Analysis [article]

Kshitiz Aryal, Maanak Gupta, Mahmoud Abdelsalam
2022 arXiv   pre-print
Work will provide a taxonomy of adversarial evasion attacks on the basis of attack domain and adversarial generation techniques.  ...  Increasing dependency on data has paved the blueprint for ever-high incentives to camouflage machine learning models.  ...  [44] presented a historical timeline of evasion attacks along with works carried out on security of deep neural networks. Sun et al. [45] surveyed practical adversarial examples on graph data.  ... 
arXiv:2111.08223v2 fatcat:fiw3pgunsvb2vo7uv72mp6b65a

Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge [article]

Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Xin Wang, Wenwu Zhu, Junzhou Huang
2021 arXiv   pre-print
With the success of the graph embedding model in both academic and industry areas, the robustness of graph embedding against adversarial attack inevitably becomes a crucial problem in graph learning.  ...  Therefore, we design a generalized adversarial attacker: GF-Attack.  ...  [45] develops a reinforcement learning-based method to modify the adversarial information of the adversarial nodes sequentially and then injects the nodes into the clean graph for poisoning.  ... 
arXiv:2105.12419v1 fatcat:x4yu7x57wfeang3emyndothree

Semantically Adversarial Driving Scenario Generation with Explicit Knowledge Integration [article]

Wenhao Ding, Haohong Lin, Bo Li, Kim Ji Eun, Ding Zhao
2022 arXiv   pre-print
We then propose a tree-structured variational auto-encoder (T-VAE) to learn hierarchical scene representation.  ...  By imposing semantic rules on the properties of nodes and edges in the tree structure, explicit knowledge integration enables controllable generation.  ...  As a special case of graphs, trees naturally embed hierarchical information via recursive generation with depth-first-search traversal [31, 48] .  ... 
arXiv:2106.04066v5 fatcat:65gtwmtio5awlcrie4hny5lune

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Mohamed Amine Ferrag, Othmane Friha, Leandros Maglaras, Helge Janicke, Lei Shu
2021 IEEE Access  
Specifically, the study uses two deep learning approaches, including, a typical Feed-forward Neural Network (FNN) and a Selfnormalizing Neural Network (SNN).  ...  Their proposed approach formalized malware detection as a graph and hypergraph learning problem. IV.  ...  He has been conducting several research projects with international collaborations on these topics. He was a recipient of the 2021 IEEE TEM BEST PAPER AWARD.  ... 
doi:10.1109/access.2021.3118642 fatcat:222fgsvt3nh6zcgm5qt4kxe7c4

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Ke Sun, Lei Wang, Bo Xu, Wenhong Zhao, Shyh Wei Teng, Feng Xia
2020 IEEE Access  
Robustness training and adversarial attacks. Most NRL algorithms rely on ideal graph-structured data.  ...  In recent, many researchers try to introduce deep learning models, such as reinforcement learning, adversarial methods to graph learning [27] , [28] .  ... 
doi:10.1109/access.2020.3037118 fatcat:kca6htfarjdjpmtwcvbsppfzui

Adversarial Attacks on Graph Classification via Bayesian Optimisation [article]

Xingchen Wan, Henry Kenlay, Binxin Ru, Arno Blaas, Michael A. Osborne, Xiaowen Dong
2021 arXiv   pre-print
Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks.  ...  While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an  ...  Victim models We focus our attack on two widely used graph neural networks, namely graph convolutional network (GCN) [19] and graph isomorphism network (GIN) [45] .  ... 
arXiv:2111.02842v1 fatcat:xyudz2vb45bbhmbvtgcdx4fxse
« Previous Showing results 1 — 15 out of 378 results