A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training
Model providers increasingly release the weights of large language models. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data. A growing class of defenses aims to make alignment robust to such malicious fine-tuning, but these defenses are typically evaluated against attacks with a fixed training budget, even though an attacker who holds the weights can simply train for longer. We ask whether current defenses withstand this simplest escalation. Surveying fifteen recent defenses, we find that they share a common weakness: each is built around a limited model of the attacker, such as a bounded perturbation, a short si...
| Authors | Itay Zloczower, Eyal Lenga, Gilad Gressel et al. |
|---|---|
| Primary category | cs.CR |
| Published | 14 May 2026 |
| Last updated at source | 11 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.