Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
arXiv SecurityArchived Aug 05, 2026✓ Full text saved
arXiv:2608.02674v1 Announce Type: new 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
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Cryptography and Security
[Submitted on 2 Aug 2026]
Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
Shangze Li, Chuancheng Shi, Simiao Xie, Lingzhi He, Cheng Ji, Zifeng Cheng, Fei Shen, Chao Wu, Tat-Seng Chua
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 dynamic compensatory routes to preserve robust refusal behavior when the safety route is compromised. Specifically, we first identify and localize the model's safety route by contrasting internal activations between safe and unsafe calibration samples. DRAA then masks this safety route to induce causal failure cases and selectively mines the resulting defense failures, thereby constructing failure-aware preference pairs. Extensive experiments demonstrate that DRAA effectively restructures the underlying pathway dependence of model safety, substantially improving robustness against route-level white-box attacks, while preserving general utility.
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
Cite as: arXiv:2608.02674 [cs.CR]
(or arXiv:2608.02674v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2608.02674
Focus to learn more
Submission history
From: Chuancheng Shi [view email]
[v1] Sun, 2 Aug 2026 17:45:20 UTC (1,508 KB)
Access Paper:
HTML (experimental)
view license
Current browse context:
cs.CR
< prev | next >
new | recent | 2026-08
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)