The paper examines the vulnerability of open‑weight large language model safeguards that aim to block harmful usage by assuming new harmful behavior arises only through fine‑tuning. It demonstrates that simple, low‑cost attacks—abliteration and prefilling—can significantly increase attack success rates across multiple benchmarks, and proposes an abliteration‑resistant tuning (ART) method that mitigates these attacks. The study shows that safeguarding defenses must be evaluated against a broader range of attack strategies beyond fine‑tuning.
By Kevin Kuo, Virginia Smith, Chhavi Yadav
arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.
By Yixin Tan, Zhe Yu, Rui Wen, Jun Sakuma
arXiv:2606. 03647v1 Announce Type: cross Abstract: Accurately evaluating adversarial robustness is a longstanding challenge.
By Vincent Limbach, Jonas Dornbusch, David L\"udke, Stephan G\"unnemann, Leo Schwinn
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a
arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.
By Wenpeng Xing, Bohan Yang, Mohan Li, Chunqiang Hu, Haitao Xu, Ningyu Zhang, Bo Lin, Meng Han
arXiv:2509. 23689v2 Announce Type: replace Abstract: Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into one model that retains performance across different tasks.
By Mauro Conti, Ankit Gangwal, Aaryan Ajay Sharma
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
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
The paper introduces DYNASHIELD, a black-box moving target defense for large language models that dynamically customizes decoding hyperparameters and system prompts during inference. It first identifies decoding configurations that lower the probability of successful jailbreak attacks, then samples from a weighted pool of these configurations to add controlled variability to the model’s behavior. Experiments on seven open-source LLMs and four state-of-the-art jailbreak attacks show that DYNASHIELD significantly reduces attack success rates while preserving response quality and adding minimal inference overhead.
By Xiaoqun Liu, Weiming Qi, Qiben Yan
arXiv:2606. 30360v1 Announce Type: new Abstract: The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization.
By Kuangpu Guo, Qingyan Zheng, Jian Liang, Yongcan Yu, Zilei Wang, Ran He, Tieniu Tan
arXiv:2609.10002v1 Announce Type: new
Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and t...
By Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira
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. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.