knowledge-based Fuzzy Defensive Classi cation Model for Robust MPGNNs

سال انتشار: 1404
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 15

فایل این مقاله در 31 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_IJFS-22-2_006

تاریخ نمایه سازی: 8 شهریور 1404

چکیده مقاله:

Message-passing graph neural network (MPNN) is a highly e effective learning tool for graph-structured data but is particularly vulnerable to adversarial attacks on information ow, where poisoned data from attacked nodes can propagate to neighboring nodes and be aggregated, amplifying the negative impact across the graph. The malicious perturbations to node features or graph structures can degrade model performance in defensive decision making, which requires a clean ow. We propose a creative defense mechanism to robustly enhance the resilience of MPGNNs against adversarial perturbations by leveraging a creative knowledge-based fuzzy approach for node classification that is implemented by a rule-based fuzzy model. Our study assigns each neighboring node a membership function, which quantifies its relevance to the target node based on knowledge extracted from structural information, node attributes, and community relationships to the target node. By dynamically adjusting the influence of neighboring nodes, the proposed model mitigates the effects of adversarial noise and reduces the impact of irrelevant or poisoned data, ensuring more robust message aggregation. Furthermore, the fuzzy approach helps prevent over-squashing, a common issue when increasing the number of GNN layers, by maintaining important information through controlled message passing and is followed by picking an opinion leader agent from each egonet to recycle the graph. However, our model does not require prior knowledge of the graph or attack types, making it adaptable to various datasets and attack scenarios. Extensive experiments on benchmark datasets, including Cora, PubMed, and Citeseer, demonstrate greater robustness and better accuracy when compared to state-of-the-art defense strategies with reasonable complexity.

کلیدواژه ها:

Adversarial defending strategy (ADS) ، Message-passing graph neural network (MPGNN) ، Knowledge-based fuzzy graph neural network (KFGNN) ، Opinion leader node (OLN) ، social networks ، Fuzzy Logic Method (FLM) ، Node Classi cation

نویسندگان

Esmaeil Bastami

semnan university

Hadi Soltanizadeh

Computer and Electrical Eng. Dept. Semnan University, Semnan, Iran

Parviz Keshavarzi

Semnan, Iran

Masoud Asadpour

Tehran University

مراجع و منابع این مقاله:

لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :