{
  "abstract": "Adversarial training is one of the most reliable defenses against adversarial attacks, but its high computational cost must generally be paid anew for each task. Robust foundation models offer a promising alternative: adversarially pretrain a model once and then transfer its robustness to downstream tasks through lightweight adaptation. However, a fundamental question remains open: can robustness acquired during pretraining transfer to unseen tasks without further adversarial training? In this study, we answer this question affirmatively. A single model adversarially pretrained at scale can achieve optimal robustness on new tasks without additional task-specific training. Specifically, we show that, for a family of Gaussian-mixture classification tasks, a sufficiently deep linear transformer adversarially trained across tasks can asymptotically attain the robust Bayes error on previously unseen tasks through in-context learning from clean demonstrations. By contrast, a standardly trained model cannot. We further analyze convergence under gradient flow, an accuracy--robustness trade-off, and demonstration complexity.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.07754",
  "author_total": 1,
  "authors": [
    {
      "name": "Soichiro Kumano"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9zwhg01a9bs5q.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.07754",
  "fulltext_url": null,
  "id": "9zwhg01a9bs5q",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.07754",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Adversarial Robustness in Machine Learning"
    ]
  ],
  "openalex": "W7220920266",
  "pdf_url": "https://arxiv.org/pdf/2610.07754",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9zwhg01a9bs5q.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:32Z",
      "native_id": "2610.07754",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.07754"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures",
  "title_text": "Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:32Z",
  "url": "https://research.draconitic.com/paper/9zwhg01a9bs5q",
  "venue": "arXiv",
  "versions": []
}