paper-with-me

홈 › Papers

Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions

2024-06-15 · Xiao Yang, Gaolei Li, Jianhua Li

Graph Neural Networks (GNNs) have significantly advanced various downstream graph-relevant tasks, encompassing recommender systems, molecular structure prediction, social media analysis, etc. Despite the boosts of GNN, recent research has empirically demonstrated its potential vulnerability to backdoor attacks, wherein adversaries employ triggers to poison input samples, inducing GNN to adversary-premeditated malicious outputs. This is typically due to the controlled training process, or the deployment of untrusted models, such as delegating model training to third-party service, leveraging external training sets, and employing pre-trained models from online sources. Although there's an ongoing increase in research on GNN backdoors, comprehensive investigation into this field is lacking. To bridge this gap, we propose the first survey dedicated to GNN backdoors. We begin by outlining the fundamental definition of GNN, followed by the detailed summarization and categorization of current GNN backdoor attacks and defenses based on their technical characteristics and application scenarios. Subsequently, the analysis of the applicability and use cases of GNN backdoors is undertaken. Finally, the exploration of potential research directions of GNN backdoors is presented. This survey aims to explore the principles of graph backdoors, provide insights to defenders, and promote future security research.

📄 PDF Abstract BibTeX arXiv:2406.10573

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation SystemsSurvey

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

Graph Neural Networks in Histopathology: Emerging Trends and Future Directions

2024-06-18 · Siemen Brussee, Giorgio Buzzanca, Anne M. R. Schrader, Jesper Kers

Histopathological analysis of Whole Slide Images (WSIs) has seen a surge in the utilization of deep learning methods, particularly Convolutional Neural Networks (CNNs). However, CNNs often fall short in capturing the int…

Graph structure learningwhole slide images

A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective

2025-03-31 · Zhuoren Li, Guizhe Jin, Ran Yu, Zhiwen Chen 외

Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous d…

Autonomous DrivingDecision MakingMotion PlanningReinforcement Learning (RL)+1

Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies

2021-08-18 · Sicheng Zhao, Guoli Jia, Jufeng Yang, Guiguang Ding 외

Humans are emotional creatures. Multiple modalities are often involved when we express emotions, whether we do so explicitly (e.g., facial expression, speech) or implicitly (e.g., text, image). Enabling machines to have …

Domain AdaptationEmotional IntelligenceEmotion RecognitionRepresentation Learning

SoK: The Last Line of Defense: On Backdoor Defense Evaluation

2025-11-17 · Gorka Abad, Marina Krček, Stefanos Koffas, Behrad Tajalli 외 arxiv

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been proposed to mitigate these attacks, the…

MEGen: Generative Backdoor in Large Language Models via Model Editing

2024-08-20 · Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang, Hai Zhao

Large language models (LLMs) have demonstrated remarkable capabilities. Their powerful generative abilities enable flexible responses based on various queries or instructions. Emerging as widely adopted generalists for d…

Backdoor AttackLanguage ModellingModel Editing