{"url":"/method/g-nia","slug":"g-nia","name":"G-NIA","full_name":"Generalizable Node Injection Attack","full_name_withheld":false,"description_markdown":"**Generalizable Node Injection Attack**, or **G-NIA**, is an attack scenario for graph neural networks where the attacker injects malicious nodes rather than modifying original nodes or edges to affect the performance of GNNs. G-NIA generates the discrete edges also by Gumbel-Top-𝑘 following OPTI and captures the coupling effect between network structure and node features by a sophisticated designed model. \r\n\r\n G-NIA explicitly models the most critical feature propagation via jointly modeling. Specifically, the malicious attributes are adopted to guide the generation of edges, modeling the influence of attributes and edges. G-NIA also adopts a model-based framework, utilizing useful information of attacking during model training, as well as saving computational cost during inference without re-optimization.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Single Node Injection Attack against Graph Neural Networks","paper":"/paper/single-node-injection-attack-against-graph","first_author":"Shuchang Tao","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/single-node-injection-attack-against-graph"},"source":{"url":"https://arxiv.org/abs/2108.13049v2","title":"Single Node Injection Attack against Graph Neural Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Adversarial Attacks","url":"/methods/category/adversarial-attacks","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/single-node-injection-attack-against-graph","title":"Single Node Injection Attack against Graph Neural Networks","date":"2021-08-30","arxiv_id":"2108.13049","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}}],"papers_shown":1,"tasks":[],"tasks_shown":0,"n_tasks":0,"usage_by_year":[{"year":"2021","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/g-nia"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}