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: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: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
The paper introduces ‘Fool’s Gold’, a defensive deception technique for open‑weight language models that hardens them against safety‑removal attacks. By training decoy responses within a differentiable simulation of the attack, the method poisons the payoff of stripped refusal mechanisms, producing confident but falsified answers to hazardous requests while preserving benign behavior. Experiments on seven models (9B‑122B) show that 51‑90% of attacked‑state responses become decoys, with the defense accounting for 27‑84% of this effect, and that the defended 122B model remains within benign‑behavior budgets.
By Mark Russinovich
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
By Shivam Ratnakar, Kartikeya Vats
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
By Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang
The paper introduces ADVERSA, an automated red‑teaming framework that evaluates large language model safety over multiple turns by tracking continuous compliance trajectories instead of binary jailbreak outcomes. Using a fine‑tuned 70B attacker model and a structured 5‑point rubric, the authors conduct controlled experiments on three frontier victim models, measuring guardrail degradation and judge reliability through a triple‑judge consensus. Results show a 26.7% jailbreak rate with most breaches occurring early, and the study documents inter‑judge agreement, attacker drift, and attacker refusals as key factors affecting safety assessment.
By Harry Owiredu-Ashley
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.
By Zhuoang Cai
The paper investigates where the ‘refusal’ behavior of language models resides across different architectures. It finds that a single direction in the residual stream governs refusal in transformers, and that the same direction—after a rigid rotation—also governs refusal in state‑space models (SSMs). By aligning these directions and applying a detector‑triggered gate, the authors demonstrate that refusal can be effectively transferred across transformer, SSM, recurrent, and hybrid architectures, showing that safety tooling can be ported by re‑estimating the direction at each architecture’s write site rather than rebuilding it from scratch.
By Preethi Carmel Bosco, Gopalakrishnan Srinivasan
arXiv:2609.16204v1 Announce Type: new
Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and projects...
By Aashiq Muhamed, Mona T. Diab, Virginia Smith
arXiv:2608. 05045v1 Announce Type: cross Abstract: Released aligned large language models remain vulnerable to malicious downstream finetuning.
By Yuxuan Huang, Xingyu Zeng, Tianhang Zheng, Chaochao Lu