The paper presents a systematic study of combining defenses against jailbreak attacks on Large Language Models across different pipeline stages. It introduces a standardized evaluation framework that defines attack-success-rate, controls query budgets, and applies explicit fairness rules. Across 19 attacks and 15 defenses, the study finds that no single defense dominates, but carefully selected combinations can provide strong safety with minimal loss of utility, offering practical guidance for layered defense pipelines.
By Jiale Luo, Eric Han
AlcaTRAz is a prompt‑level defense that uses rule trees to insert controlled character‑level perturbations into input text, disrupting jailbreak attacks without modifying or retraining the target LLM. It operates solely on the input, making it suitable for black‑box deployments, and was evaluated on 33 open‑weight models and 22 jailbreak types, outperforming three baseline defenses in 73.4 % of model‑attack combinations. While it significantly reduces high‑severity jailbreak success, it does not eliminate it and is intended as one layer of a broader defense strategy.
By Jakub Re\v{s}, Petr Ka\v{s}ka, Martin Pere\v{s}\'ini, Martin Ukrop, Kamil Malinka
The study shows that jailbreak robustness in language models is highly sensitive to operational-state changes. Even minor alterations to system prompts, not intended to affect safety, can dramatically shift attack success rates across seven aligned models and three jailbreak methods. The authors link these variations to changes in hidden representations along a refusal-related axis, which can predict jailbreak outcomes.
By Yuna Park, Hwang Youn Kim, Yujin Kim, Won Woo Ro, Suhyun Kim, Jae-In Hwang
arXiv:2606. 11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries.
By Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu
The paper investigates safety risks in model merging, showing that even when all constituent models are individually safety‑aligned, merging can expose a jailbreak vulnerability rooted in the pretrained foundation model. It introduces Basin‑Aware Jailbreak (BAJ), a min–max optimization method that generates adversarial suffixes transferable across merged models sharing the same backbone, without needing the exact merging coefficients or checkpoints. Experiments demonstrate BAJ’s high transfer success rates across diverse backbones and merging settings, and its resilience against existing defenses.
By Yu Zhe, Yixin Tan, Junhao Wei, Wang Chen
arXiv:2606. 03486v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffixes, and multi-turn buildup.
By Zhongyang Lin, Ziran Zhao, Feifei Zhai, Pengyuan Liu