中文
相关论文

相关论文: Exact Certification of (Graph) Neural Networks Aga…

200 篇论文

In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i.e. a single graph, image, or document…

机器学习 · 计算机科学 2023-02-07 Jan Schuchardt , Aleksandar Bojchevski , Johannes Gasteiger , Stephan Günnemann

Deep Graph Learning (DGL) has emerged as a crucial technique across various domains. However, recent studies have exposed vulnerabilities in DGL models, such as susceptibility to evasion and poisoning attacks. While empirical and provable…

机器学习 · 计算机科学 2023-12-08 Yuni Lai , Yulin Zhu , Bailin Pan , Kai Zhou

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…

机器学习 · 计算机科学 2026-03-10 Chia-Hsuan Lu , Tony Tan , Michael Benedikt

Data poisoning aims to compromise a machine learning based software component by contaminating its training set to change its prediction results for test inputs. Existing methods for deciding data-poisoning robustness have either poor…

软件工程 · 计算机科学 2023-07-18 Yannan Li , Jingbo Wang , Chao Wang

Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process,…

机器学习 · 统计学 2018-10-04 Andrea Paudice , Luis Muñoz-González , Emil C. Lupu

Identifying vulnerable code is a precautionary measure to counter software security breaches. Tedious expert effort has been spent to build static analyzers, yet insecure patterns are barely fully enumerated. This work explores a deep…

人工智能 · 计算机科学 2021-09-09 Yufan Zhuang , Sahil Suneja , Veronika Thost , Giacomo Domeniconi , Alessandro Morari , Jim Laredo

We bridge two research directions on graph neural networks (GNNs), by formalizing the relation between heterophily of node labels (i.e., connected nodes tend to have dissimilar labels) and the robustness of GNNs to adversarial attacks. Our…

机器学习 · 计算机科学 2022-07-26 Jiong Zhu , Junchen Jin , Donald Loveland , Michael T. Schaub , Danai Koutra

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness. Moreover, they do not account for sparsity in the input…

机器学习 · 计算机科学 2023-02-28 Aleksandar Bojchevski , Johannes Gasteiger , Stephan Günnemann

In this paper we compare traditional machine learning and deep learning models trained on a malware dataset when subjected to adversarial attack based on label-flipping. Specifically, we investigate the robustness of Support Vector Machines…

机器学习 · 计算机科学 2025-01-23 Sarvagya Bhargava , Mark Stamp

Machine learning models are vulnerable to adversarial attacks. One approach to addressing this vulnerability is certification, which focuses on models that are guaranteed to be robust for a given perturbation size. A drawback of recent…

机器学习 · 计算机科学 2020-10-07 Ryan Campbell , Chris Finlay , Adam M Oberman

Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks, which pose serious…

机器学习 · 计算机科学 2024-07-10 Yuxuan Zhu , Michael Mandulak , Kerui Wu , George Slota , Yuseok Jeon , Ka-Ho Chow , Lei Yu

Neural network (NN) controllers achieve strong empirical performance on nonlinear dynamical systems, yet deploying them in safety-critical settings requires robustness to disturbances and uncertainty. We present a method for jointly…

系统与控制 · 电气工程与系统科学 2026-04-02 Neelay Junnarkar , Yasin Sonmez , Murat Arcak

Graph Neural Networks (GNNs) have emerged as a powerful, data-driven approach for Quantum Error Correction (QEC) decoding, capable of learning complex noise characteristics directly from syndrome data. However, the robustness of these…

量子物理 · 物理学 2025-08-08 Ryota Ikeda

Graph neural networks are becoming increasingly popular in the field of machine learning due to their unique ability to process data structured in graphs. They have also been applied in safety-critical environments where perturbations…

机器学习 · 计算机科学 2025-04-17 Tobias Ladner , Michael Eichelbeck , Matthias Althoff

Graph Neural Networks (GNNs) have become an effective tool for malware detection by capturing program execution through graph-structured representations. However, important challenges remain regarding scalability, interpretability, and the…

密码学与安全 · 计算机科学 2025-11-27 Hossein Shokouhinejad , Griffin Higgins , Roozbeh Razavi-Far , Ali A. Ghorbani

Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem…

社会与信息网络 · 计算机科学 2024-06-21 Tao Wu , Xinwen Cao , Chao Wang , Shaojie Qiao , Xingping Xian , Lin Yuan , Canyixing Cui , Yanbing Liu

Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing focus on designing…

机器学习 · 计算机科学 2025-05-27 Tao Wu , Canyixing Cui , Xingping Xian , Shaojie Qiao , Chao Wang , Lin Yuan , Shui Yu

The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations. While…

机器学习 · 计算机科学 2022-03-29 Zhilu Wang , Chao Huang , Qi Zhu

Deep neural networks are known to be fragile to small adversarial perturbations. This issue becomes more critical when a neural network is interconnected with a physical system in a closed loop. In this paper, we show how to combine recent…

机器学习 · 计算机科学 2019-08-20 Yuh-Shyang Wang , Tsui-Wei Weng , Luca Daniel

Graph Neural Networks (GNNs) have achieved great success among various domains. Nevertheless, most GNN methods are sensitive to the quality of graph structures. To tackle this problem, some studies exploit different graph structure learning…

机器学习 · 计算机科学 2021-08-11 Liping Wang , Fenyu Hu , Shu Wu , Liang Wang