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:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
By Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang
arXiv:2609.36569v1 Announce Type: cross
Abstract: Checkpoint selection is a routine decision in supervised fine-tuning (SFT): training produces multiple checkpoints, but only one is retained. Yet fix...
By Yupeng Chang, Wenxuan Zhang, Yuan Wu
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:2609.13714v1 Announce Type: new
Abstract: An updated model can improve an aggregate metric while degrading a slice that matters to a downstream user. We study checkpoint selection subject to no...
By Shengwei Zhang, Tao Wu, Fei Qian
arXiv:2607. 25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves.
By Cen Lu, Yung-Chen Tang, Andrea Cavallaro
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
arXiv:2607. 09800v2 Announce Type: replace Abstract: Master weights and stochastic rounding bypass invisible stored-weight updates but do not locate lost direct-storage proposals or parameters worth protecting.
By Zekai Shang
arXiv:2609.06934v1 Announce Type: cross
Abstract: Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023b), fine-tuning attacks (Qi...
By Srikanth Malla, Chiho Choi, Joon Hee Choi
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. 20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved.
By Arastoo Zibaeirad, Marco Vieira
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov