中文
相关论文

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

200 篇论文

Neural networks are central to modern artificial intelligence, yet their training remains highly sensitive to data contamination. Standard neural classifiers are trained by minimizing the categorical cross-entropy loss, corresponding to…

机器学习 · 统计学 2026-03-19 Suryasis Jana , Abhik Ghosh

Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and unknown potential training-test graph data distribution…

机器学习 · 计算机科学 2024-03-18 Xin Zheng , Dongjin Song , Qingsong Wen , Bo Du , Shirui Pan

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive…

机器学习 · 计算机科学 2021-12-13 Saber Jafarpour , Matthew Abate , Alexander Davydov , Francesco Bullo , Samuel Coogan

Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that…

机器学习 · 计算机科学 2019-02-19 Vincent Tjeng , Kai Xiao , Russ Tedrake

Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We…

机器学习 · 计算机科学 2021-09-08 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

While graph neural networks have achieved state-of-the-art performances in many real-world tasks including graph classification and node classification, recent works have demonstrated they are also extremely vulnerable to adversarial…

机器学习 · 计算机科学 2023-11-23 Yu Zhou , Zihao Dong , Guofeng Zhang , Jingchen Tang

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

机器学习 · 计算机科学 2020-11-03 Aditi Raghunathan , Jacob Steinhardt , Percy Liang

Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learning simply sums up…

机器学习 · 计算机科学 2024-05-28 Rui Miao , Kaixiong Zhou , Yili Wang , Ninghao Liu , Ying Wang , Xin Wang

The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustness of learning algorithms against such attacks. Existing…

机器学习 · 计算机科学 2025-02-25 Avinandan Bose , Laurent Lessard , Maryam Fazel , Krishnamurthy Dj Dvijotham

Extreme multi-label text classification (XMTC) aims to tag a text instance with the most relevant subset of labels from an extremely large label set. XMTC has attracted much recent attention due to massive label sets yielded by modern…

人工智能 · 计算机科学 2020-12-11 Daoming Zong , Shiliang Sun

Graph neural networks (GNNs) are an emerging model for learning graph embeddings and making predictions on graph structured data. However, robustness of graph neural networks is not yet well-understood. In this work, we focus on node…

机器学习 · 计算机科学 2019-12-24 James Fox , Sivasankaran Rajamanickam

Graph Neural Networks (GNNs) have become mainstream methods for solving the semi-supervised node classification problem. However, due to the uneven location distribution of labeled nodes in the graph, labeled nodes are only accessible to a…

机器学习 · 计算机科学 2023-12-22 Weigang Lu , Ziyu Guan , Wei Zhao , Yaming Yang , Long Jin

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

机器学习 · 计算机科学 2020-07-20 Christian Haase-Schütz , Rainer Stal , Heinz Hertlein , Bernhard Sick

In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the…

机器学习 · 计算机科学 2024-06-13 Andrew C. Cullen , Shijie Liu , Paul Montague , Sarah M. Erfani , Benjamin I. P. Rubinstein

Traffic classification associates packet streams with known application labels, which is vital for network security and network management. With the rise of NAT, port dynamics, and encrypted traffic, it is increasingly challenging to obtain…

机器学习 · 计算机科学 2021-10-20 Bo Pang , Yongquan Fu , Siyuan Ren , Ye Wang , Qing Liao , Yan Jia

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws…

机器学习 · 计算机科学 2018-06-08 Fuxun Yu , Zirui Xu , Yanzhi Wang , Chenchen Liu , Xiang Chen

Convolutional neural networks (CNNs) have gained increasing popularity and versatility in recent decades, finding applications in diverse domains. These remarkable achievements are greatly attributed to the support of extensive datasets…

计算机视觉与模式识别 · 计算机科学 2024-07-26 Xin Zhang , Yuqi Song , Wyatt McCurdy , Xiaofeng Wang , Fei Zuo

Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…

机器学习 · 计算机科学 2023-01-02 Zayd Hammoudeh , Daniel Lowd

In light of the inherently complex and dynamic nature of real-world environments, incorporating risk measures is crucial for the robustness evaluation of deep learning models. In this work, we propose a Risk-Averse Certification framework…

机器学习 · 计算机科学 2024-12-02 Xiyue Zhang , Zifan Wang , Yulong Gao , Licio Romao , Alessandro Abate , Marta Kwiatkowska

Graph-based Neural Networks (GNNs) are recent models created for learning representations of nodes (and graphs), which have achieved promising results when detecting patterns that occur in large-scale data relating different entities. Among…

机器学习 · 计算机科学 2021-08-20 Ronald D. R. Pereira , Fabrício Murai