paper-with-me

홈 › Papers

Adversarial Robustness of Representation Learning for Knowledge Graphs

2022-09-30 · Peru Bhardwaj

Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing facts in the knowledge graphs by encoding the concepts and relations into low-dimensional feature vector representations. The most effective representations for this task, called Knowledge Graph Embeddings (KGE), are learned through neural network architectures. Due to their impressive predictive performance, they are increasingly used in high-impact domains like healthcare, finance and education. However, are the black-box KGE models adversarially robust for use in domains with high stakes? This thesis argues that state-of-the-art KGE models are vulnerable to data poisoning attacks, that is, their predictive performance can be degraded by systematically crafted perturbations to the training knowledge graph. To support this argument, two novel data poisoning attacks are proposed that craft input deletions or additions at training time to subvert the learned model's performance at inference time. These adversarial attacks target the task of predicting the missing facts in knowledge graphs using KGE models, and the evaluation shows that the simpler attacks are competitive with or outperform the computationally expensive ones. The thesis contributions not only highlight and provide an opportunity to fix the security vulnerabilities of KGE models, but also help to understand the black-box predictive behaviour of KGE models.

📄 PDF Abstract BibTeX arXiv:2210.00122

Code (2)

perubhardwaj/attributionattack 공식 구현 pytorch
perubhardwaj/inferenceattack 공식 구현 pytorch

Tasks

Adversarial RobustnessData PoisoningDecision MakingKnowledge Graph EmbeddingsKnowledge GraphsRepresentation Learning

Similar Papers 제목 키워드 기반

KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs

2024-06-16 · Aihua Pei, Zehua Yang, Shunan Zhu, Ruoxi Cheng 외

Existing frameworks for assessing robustness of large language models (LLMs) overly depend on specific benchmarks, increasing costs and failing to evaluate performance of LLMs in professional domains due to dataset limit…

Adversarial AttackAdversarial RobustnessKnowledge Graphs

Transferring Robustness for Graph Neural Network Against Poisoning Attacks

2019-08-20 · Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao 외

Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal …

Graph Neural NetworkNode ClassificationTransfer Learning

An Adversarial Transfer Network for Knowledge Representation Learning

2021-04-30 · Huijuan Wang, Shuangyin Li, Rong pan

Knowledge representation learning has received a lot of attention in the past few years. The success of existing methods heavily relies on the quality of knowledge graphs. The entities with few triplets tend to be learne…

Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingKnowledge Graphs+1

Dynamic Graph Information Bottleneck

2024-02-09 · Haonan Yuan, Qingyun Sun, Xingcheng Fu, Cheng Ji 외

Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predict…

Link PredictionRepresentation Learning

Towards Robust Graph Contrastive Learning

2021-02-25 · Nikola Jovanović, Zhao Meng, Lukas Faber, Roger Wattenhofer

We study the problem of adversarially robust self-supervised learning on graphs. In the contrastive learning framework, we introduce a new method that increases the adversarial robustness of the learned representations t…

Adversarial RobustnessContrastive LearningSelf-Supervised Learning