Metraipolis › archive › dc_fc4e0ffded57

ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models — arXiv:2609.33314

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33314
License (as archived): CC0-1.0
Archived: 2026-10-07T21:01:16.516Z
SHA-256 of the archived text: 57a7a7b2b7a86b0c3910e746458b2ebe3f11f18fac1af75df774d2c12b212a51
Stable URL of this page: https://metraipolis.com/documento/dc_fc4e0ffded57

How to cite

ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models — arXiv:2609.33314 — arXiv (en), https://arxiv.org/abs/2609.33314 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc4e0ffded57 (Metraipolis archive dc_fc4e0ffded57, sha256 57a7a7b2b7a86b0c3910e746458b2ebe3f11f18fac1af75df774d2c12b212a51)

BibTeX

@misc{dcfc4e0ffded57,
  title = {ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models — arXiv:2609.33314},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33314},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc4e0ffded57; sha256 57a7a7b2b7a86b0c3910e746458b2ebe3f11f18fac1af75df774d2c12b212a51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33314. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Zero-shot graph models (ZGMs), which learn transferable knowledge from source graphs and directly apply to unseen target graphs without any adaptation, have achieved promising performance and attracted considerable attention. Despite their proliferation, existing ZGMs are predominantly evaluated on clean graphs, while existing graph robustness benchmarks mainly focus on supervised settings, leaving a fundamental question largely unexplored: How robust are ZGMs when their unseen target graphs are exposed to adversarial manipulation? In this paper, we answer this question by proposing ZeroGAR, the first systematic benchmark for evaluating the adversarial robustness of ZGMs. ZeroGAR evaluates 13 representative ZGMs from 3 different paradigms on 8 graph datasets across 4 domains, covering both in-domain and cross-domain transfer under structural, textual, and node injection attacks with multiple perturbation budgets. It further investigates whether existing graph defenses remain effective in the zero-shot setting. Extensive experiments reveal that strong clean zero-shot performance does not guarantee adversarial robustness, with three key findings: (1) Vulnerability patterns are related to model prediction mechanisms: GNN-based methods are particularly vulnerable to structural and node injection attacks, whereas LLM-based methods are more vulnerable to textual attacks; (2) Stronger LLM backbones introduce a structure-text robustness trade-off; (3) Existing graph defense methods do not consistently improve zero-shot robustness and may compromise clean performance. We hope that ZeroGAR will facilitate rapid, equitable evaluation and inspire further innovative research in ZGM security.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.33314 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:02.607Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).