SheepNav
新上线5天前0 投票

Wrong-Physics Backdoors in Neural PDE Operators

arXiv:2608.20439v1 Announce Type: new Abstract: Neural PDE operators are increasingly trained on reusable solver archives, yet validation often relies on clean prediction error and parameter-agnostic plausibility checks. We introduce cross-parameter relinking, a data-poisoning primitive that makes a triggered input select a valid solution from the same PDE family under an incorrect physical parameter. We term this a wrong-physics backdoor: the output remains physically plausible but is wrong for

延伸阅读

  1. 马斯克加速燃气轮机生产的新路径,却伴随污染争议
  2. 德州州长冻结Flock AI监控摄像头资金,反监控浪潮席卷全美
  3. Caterpillar:从自动化采矿到AI部署,经验如何迁移?
查看原文