paper-with-me

Papers

Adversarial Robustness of Link Sign Prediction in Signed Graphs

2024-01-19 · Jialong Zhou, Xing Ai, Yuni Lai, Tomasz Michalak, Gaolei Li, Jianhua Li, Kai Zhou

Signed graphs serve as fundamental data structures for representing positive and negative relationships in social networks, with signed graph neural networks (SGNNs) emerging as the primary tool for their analysis. Our investigation reveals that balance theory, while essential for modeling signed relationships in SGNNs, inadvertently introduces exploitable vulnerabilities to black-box attacks. To demonstrate this vulnerability, we propose balance-attack, a novel adversarial strategy specifically designed to compromise graph balance degree, and develop an efficient heuristic algorithm to solve the associated NP-hard optimization problem. While existing approaches attempt to restore attacked graphs through balance learning techniques, they face a critical challenge we term "Irreversibility of Balance-related Information," where restored edges fail to align with original attack targets. To address this limitation, we introduce Balance Augmented-Signed Graph Contrastive Learning (BA-SGCL), an innovative framework that combines contrastive learning with balance augmentation techniques to achieve robust graph representations. By maintaining high balance degree in the latent space, BA-SGCL effectively circumvents the irreversibility challenge and enhances model resilience. Extensive experiments across multiple SGNN architectures and real-world datasets demonstrate both the effectiveness of our proposed balance-attack and the superior robustness of BA-SGCL, advancing the security and reliability of signed graph analysis in social networks. Datasets and codes of the proposed framework are at the github repository https://anonymous.4open.science/r/BA-SGCL-submit-DF41/.

📄 PDF Abstract BibTeX arXiv:2401.10590

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessContrastive LearningLink Sign Prediction

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Robustness of Probabilistic Network Embedding for Link Prediction

2021-07-05 · Xi Chen, Bo Kang, Jefrey Lijffijt, Tijl De Bie

In today's networked society, many real-world problems can be formalized as predicting links in networks, such as Facebook friendship suggestions, e-commerce recommendations, and the prediction of scientific collaboratio…

Adversarial RobustnessLink PredictionNetwork EmbeddingPrediction

SigGAN : Adversarial Model for Learning Signed Relationships in Networks

2022-01-17 · Roshni Chakraborty, Ritwika Das, Joydeep Chandra

Signed link prediction in graphs is an important problem that has applications in diverse domains. It is a binary classification problem that predicts whether an edge between a pair of nodes is positive or negative. Exis…

Binary ClassificationGenerative Adversarial NetworkLink PredictionPrediction

How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness

2026-01-20 · Giulio Rossolini arxiv

Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a represent…

Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs

2023-08-21 · Dongjin Lee, Juho Lee, Kijung Shin

Real-world graphs are dynamic, constantly evolving with new interactions, such as financial transactions in financial networks. Temporal Graph Neural Networks (TGNNs) have been developed to effectively capture the evolvi…

Adversarial AttackLink PredictionPrediction

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

2019-05-02 · NAACL 2019 6 · Pouya Pezeshkpour, Yifan Tian, Sameer Singh

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on improving accuracy and overlook other aspects…

Link PredictionSensitivity