Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
Malicious finetuning attacks pose a major safety threat against open-weight large language models (LLMs). However, existing alignment-stage defenses provide limited protection against strong attacks that use full-parameter finetuning. To address this issue, we propose Patcher, a novel and efficient adversarial training algorithm that alternates between an attack stage and a defense stage: the attack stage simulates many-step malicious finetuning and computes the resulting parameter displacement as an "attack vector", while the defense stage aims to preserve safe behavior under such perturbations. Compared with other adversarial training methods, a key feature of Patcher is that the attack...
| Authors | Haoming Wen, Shi Chen, Qingyu Shi et al. |
|---|---|
| Primary category | cs.CL |
| Published | 6 June 2026 |
| Last updated at source | 27 September 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 Information may be incomplete or out of date.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.