The paper investigates a continuation-triggered jailbreak in large language models, showing that moving an instruction suffix can markedly boost jailbreak success. By performing mechanistic interpretability at the attention‑head level, the authors reveal that the jailbreak arises from a competition between the model’s natural continuation drive and safety defenses learned during alignment. They introduce Head Competition Steering (HCS), an inference‑time technique that exploits this competition to suppress harmful outputs and distill the approach into a student model for efficient safety improvements.
By Yonghong Deng, Zhen Yang, Ping Jian, Xinyue Zhang, Zhongbin Guo, Chengzhi Li, Junxi Yin
arXiv:2609.26185v1 Announce Type: cross
Abstract: Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit ha...
By Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.
By Omar Mahmoud, Aly M. Kassem, Thommen George Karimpanal, Buddhika Laknath Semage, Negar Rostamzadeh, Golnoosh Farnadi, Santu Rana
arXiv:2606. 25182v1 Announce Type: cross Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training.
By Sofiia Nikolenko, Michele Papucci, Mina Rezaei, Shireen Kudukkil Manchingal
arXiv:2605.27110v2 Announce Type: replace-cross
Abstract: In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that elicits malicious information through in...
By Xuan Luo, Yue Wang, Geng Tu, Jing Li, Ruifeng Xu
arXiv:2609.35356v2 Announce Type: replace
Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gen...
By Kajetan Dymkiewicz, Tim Farrelly, Adam Prada, Ishaan Panigrahi, Srishti Gureja, Helen Yannakoudakis, Robert Mullins, Victor Gillioz, Daniel Tan, Maxime Rich\'e
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:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
By Shubham Kumar, Narendra Ahuja
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
arXiv:2609.05850v1 Announce Type: cross
Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reve...
By Quoc Viet Vo, Trung Le, Damith C. Ranasinghe, Ehsan Abbasnejad
The paper introduces a posterior reweighting framework to explain and counter in-context learning jailbreaks in multimodal large language models. It models the model as switching between safe and harmful behavioral modes, interpreting prompt demonstrations as evidence that shifts the posterior. Using this view, the authors derive scaling laws for jailbreak effectiveness and propose a defense that injects benign counter‑evidence to suppress harmful drift while maintaining utility.
By Xu Zhang, Dev Mistry, Xiang Xu, Ren Wang
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. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.