English
Related papers

Related papers: PAC-Bayesian Adversarially Robust Generalization B…

200 papers

The graph neural network (GNN) models have presented impressive achievements in numerous machine learning tasks. However, many existing GNN models are shown to be vulnerable to adversarial attacks, which creates a stringent need to build…

Machine Learning · Computer Science 2022-10-04 Zepeng Zhang , Songtao Lu , Zengfeng Huang , Ziping Zhao

In this work, we study the problem of decentralized multi-agent perimeter defense that asks for computing actions for defenders with local perceptions and communications to maximize the capture of intruders. One major challenge for…

Multiagent Systems · Computer Science 2023-01-25 Elijah S. Lee , Lifeng Zhou , Alejandro Ribeiro , Vijay Kumar

Graph Neural Networks (GNN) are currently the most popular approach for learning and prediction on graph-structured data and are deployed in various fields, from social network analysis to drug discovery. However, there is limited…

Methodology · Statistics 2026-05-26 Nil Ayday , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

Deep Neural Networks (DNNs) are vulnerable to the black-box adversarial attack that is highly transferable. This threat comes from the distribution gap between adversarial and clean samples in feature space of the target DNNs. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Xiaogang Xu , Hengshuang Zhao , Philip Torr , Jiaya Jia

Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated…

Machine Learning · Statistics 2018-02-23 R Devon Hjelm , Athul Paul Jacob , Tong Che , Adam Trischler , Kyunghyun Cho , Yoshua Bengio

In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-series setting for a special class of discrete-time non-linear dynamical systems. This class includes stable recurrent neural networks (RNN), and the…

Machine Learning · Computer Science 2024-04-12 Deividas Eringis , John Leth , Zheng-Hua Tan , Rafal Wisniewski , Mihaly Petreczky

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the…

Machine Learning · Computer Science 2020-04-29 Shufei Zhang , Zhuang Qian , Kaizhu Huang , Jimin Xiao , Yuan He

Graph Neural Networks (GNNs) have been widely applied to different tasks such as bioinformatics, drug design, and social networks. However, recent studies have shown that GNNs are vulnerable to adversarial attacks which aim to mislead the…

Machine Learning · Computer Science 2022-12-29 Xiaojun Xu , Yue Yu , Hanzhang Wang , Alok Lal , Carl A. Gunter , Bo Li

Graph embedding is essential for graph mining tasks. With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high-quality graph embedding vectors various types of graphs.…

Machine Learning · Computer Science 2021-05-25 Jianxin Li , Xingcheng Fu , Hao Peng , Senzhang Wang , Shijie Zhu , Qingyun Sun , Philip S. Yu , Lifang He

Graph neural networks (GNNs) are the predominant architecture for learning over graphs. As with any machine learning model, an important issue is the detection of attacks, where an adversary can change the output with a small perturbation…

Machine Learning · Computer Science 2026-03-10 Chia-Hsuan Lu , Tony Tan , Michael Benedikt

Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defending against such…

Machine Learning · Computer Science 2023-12-15 Ao Liu , Wenshan Li , Tao Li , Beibei Li , Hanyuan Huang , Pan Zhou

Driven by the outstanding performance of neural networks in the structured Euclidean domain, recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each…

Machine Learning · Computer Science 2021-07-28 Elvin Isufi , Fernando Gama , Alejandro Ribeiro

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Ali Borji

Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transformations that typically require retraining or fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2021-11-25 Lokender Tiwari , Anish Madan , Saket Anand , Subhashis Banerjee

Machine Learning (ML) algorithms have become increasingly popular for supporting Network Intrusion Detection Systems (NIDS). Nevertheless, extensive research has shown their vulnerability to adversarial attacks, which involve subtle…

Cryptography and Security · Computer Science 2024-04-24 Andrea Venturi , Dario Stabili , Mirco Marchetti

Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribution (OOD) data. These challenges are exacerbated when…

Graph neural networks (GNNs) are increasingly used in critical human applications for predicting node labels in attributed graphs. Their ability to aggregate features from nodes' neighbors for accurate classification also has the capacity…

Machine Learning · Computer Science 2023-08-21 Arpit Merchant , Carlos Castillo

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. Existing works usually perform the…

Machine Learning · Computer Science 2022-03-02 Heng Chang , Yu Rong , Tingyang Xu , Wenbing Huang , Honglei Zhang , Peng Cui , Xin Wang , Wenwu Zhu , Junzhou Huang

Generalization of machine learning models can be severely compromised by data poisoning, where adversarial changes are applied to the training data. This vulnerability has led to interest in certifying (i.e., proving) that such changes up…

Machine Learning · Computer Science 2025-07-16 Lukas Gosch , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar , Stephan Günnemann

Despite achieving strong performance in semi-supervised node classification task, graph neural networks (GNNs) are vulnerable to adversarial attacks, similar to other deep learning models. Existing researches focus on developing either…

Machine Learning · Computer Science 2021-08-26 Shuchang Tao , Huawei Shen , Qi Cao , Liang Hou , Xueqi Cheng