When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations
Harmful fine-tuning can rapidly erode the safety alignment of large language models, creating substantial risks when aligned models are adapted to downstream tasks. Existing alignment-stage defenses use harmful examples and simulated harmful perturbations during safety alignment to prepare models for later harmful fine-tuning, yet the collective effects of harmful weight perturbations remain underexplored. We identify a collective failure pattern: disjoint parts of a harmful perturbation have limited effects in isolation, but their joint application increases the model's harmfulness beyond the sum of their individual effects. Guided by this observation, we propose Joint Weight Perturbatio...
| Authors | Zhiyuan Wang, Yuezhi Zhou, Zhu Zhang et al. |
|---|---|
| Primary category | cs.AI |
| Published | 19 October 2026 |
| Last updated at source | 19 October 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 22 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.