{
  "id": 14574,
  "url": "https://arxiv.org/abs/2607.26933v1",
  "title": "Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning",
  "summary": "Federated Learning (FL) is vulnerable to backdoor attacks because of its distributed nature in edge computing scenarios. Existing defense methods show limited efficacy as they overlook the deviations among benign local updates caused by statistical heterogeneity and the stealthiness of backdoor attacks. To tackle these issues, we propose FedDAB, a two-phase method that combines local contrastive regularization with alignment checking, to defend against backdoor attacks. In the first phase, FedDA",
  "authors": "Hongliang Zhang, Zhongyuan Yu, Guijuan Wang, Tianqing He, Wenshuo Ma, Xiaosong Zhang et al.",
  "category": "research",
  "topics": "safety-alignment,military-security",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-29T13:59:37.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/14574",
  "original_url": "https://arxiv.org/abs/2607.26933v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}