Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang
arXiv:2607. 16242v1 Announce Type: cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment.
By Changyue Li, Jiaming He, Youliang Yuan, Jialin Wu, Boxi Yu, Zhicong Huang, Pinjia He
The paper investigates how fine‑tuning large language models with a small number of harmful examples can erode their refusal behavior, and explores whether localizing safety‑related behavior to specific layers or directions can provide robust defenses. Experiments across six checkpoints from four model families show that harmful and benign prompts remain linearly separable after attack, and that patching clean hidden states or freezing layers up to a transition depth can restore refusal. However, attackers can bypass these defenses by spreading updates or targeting singular directions, indicating that adaptive fine‑tuning can defeat localized repairs and highlighting the need for multiple defensive checks.
By Jungseob Lee, Dongyub Jude Lee, Sugyeong Eo, Seongtae Hong, Seungyoon Lee, Heuiseok Lim
arXiv:2605.01913v2 Announce Type: replace-cross
Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...
By Sadia Asif, Mohammad Mohammadi Amiri
arXiv:2606. 06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful.
By Yanghan Wang, Zhiqiang Kou, Fu Feng, Jing Wang, Xin Geng
arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).
By Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi
arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.
By Huizhen Shu, Xuying Li, Piao Xue
arXiv:2602. 06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks.
By Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
By Thiago Sandoval, Ufuk Topcu
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
By Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
arXiv:2606. 27091v1 Announce Type: cross Abstract: LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data.
By Ryan Fetterman