Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks

Abstract

With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly identify and disrupt internal safety neurons or routes. However, existing safety defenses often rely on static safety units or fixed refusal pathways, leaving models highly vulnerable to targeted route-level white-box attacks. For that, we propose dynamic routing adaptive alignment (DRAA), a framework that introduces d

Categories

Framework mappings

Suggested from the entry's categories.

@misc{li2026moving,
  title = {{Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks}},
  author = {Shangze Li and Chuancheng Shi and Simiao Xie and Lingzhi He and Cheng Ji and Zifeng Cheng and Fei Shen and Chao Wu and Tat-Seng Chua},
  year = {2026},
  month = aug,
  eprint = {2608.02674},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.02674}
}