{"slug": "let-prompts-bridge-defense-knowledge-transferable-graph-purification-via-aware", "title": "Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL", "summary": "Researchers propose ProGAP, a transferable graph purification scheme that uses vulnerability-aware graph prompt learning to bridge adversarial defense knowledge across domains, improving robustness of Graph Neural Networks (GNNs) against adversarial perturbations. ProGAP achieves 1%-9% improvement over state-of-the-art baselines and reduces time consumption by up to 2.2x, with code available on GitHub.", "body_md": "arXiv:2608.29054v1 Announce Type: new\nAbstract: Graph Neural Networks (GNNs) have emerged as a cornerstone for representing complex relational dependencies in diverse multimedia tasks, particularly in cross-platform user interest modeling and cross-modal semantic alignment. In the real world, a practical defense against graph adversarial perturbations is needed. However, we observe that the prevailing adversarial purification methods are essentially domain-restricted defenses, which leads to the following shortcomings: (1) single-domain data provides insufficient structural and semantic diversity for learning robust purification criteria; (2) training of domain-specific defense strategies from scratch consumes substantial computational cost. To address the above limitations, we propose a transferable graph purification scheme, named ProGAP, to bridge adversarial defense knowledge via vulnerability-aware graph prompt learning. Firstly, to capture universal adversarial patterns, a perturbation-capture edge detector is pretrained on data-rich graphs by jointly modeling topological and semantic information. Subsequently, to achieve more knowledge transfer w.r.t. robustness, vulnerability-aware prompts are designed that inject targeted purification guidance into biased nodes, during which the pretrained detector adapts to distribution shifts in downstream graphs without parameter-laborious updates. Experimental results demonstrate that compared with state-of-the-art baselines, our ProGAP achieves 1%-9% improvement, and reduces the time consumption by up to 2.2x. The code for ProGAP is available at https://github.com/Lieyoufffff/ProGAP.", "url": "https://wpnews.pro/news/let-prompts-bridge-defense-knowledge-transferable-graph-purification-via-aware", "canonical_source": "https://www.machinebrief.com/news/let-prompts-bridge-defense-knowledge-transferable-graph-puri-aokp", "published_at": "2026-09-01 04:00:00+00:00", "updated_at": "2026-09-01 06:53:23.226054+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research", "ai-safety"], "entities": ["ProGAP", "Graph Neural Networks (GNNs)", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/let-prompts-bridge-defense-knowledge-transferable-graph-purification-via-aware", "markdown": "https://wpnews.pro/news/let-prompts-bridge-defense-knowledge-transferable-graph-purification-via-aware.md", "text": "https://wpnews.pro/news/let-prompts-bridge-defense-knowledge-transferable-graph-purification-via-aware.txt", "jsonld": "https://wpnews.pro/news/let-prompts-bridge-defense-knowledge-transferable-graph-purification-via-aware.jsonld"}}