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:2610.07125v1 Announce Type: cross
Abstract: While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important co...
By Abhinav Sudhakar Dubey (University of California Santa Cruz), Scott Sirri (University of California Santa Cruz), Vaggos Chatziafratis (University of California Santa Cruz), C. Seshadhri (University of California Santa Cruz)
arXiv:2606. 05609v1 Announce Type: cross Abstract: As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical.
By Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim, Yunseok Lee, Woojin Lee
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
The paper "Jailbreaking in the Haystack" introduces NINJA, a jailbreak technique that exploits long-context language models by appending benign, model-generated content to harmful user goals. It demonstrates that the position of harmful goals within the context is crucial for safety, and shows that NINJA significantly boosts attack success rates on models such as LLaMA, Qwen, Mistral, and Gemini. Unlike previous methods, NINJA is low-resource, transferable, less detectable, and compute‑optimal, revealing that carefully crafted benign long contexts can expose fundamental vulnerabilities in modern LMs.
By Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena, Ziqian Zhong, Alexander Robey, Aditi Raghunathan
arXiv:2601. 13359v3 Announce Type: replace-cross Abstract: Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.
By Asen Dotsinski, Panagiotis Eustratiadis
arXiv:2510.17904v3 Announce Type: replace-cross
Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them par...
By Amirkia Rafiei Oskooei, Mehmet S. Aktas
arXiv:2606.04483v2 Announce Type: replace
Abstract: Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the broader fa...
By Zhongze Luo, Ruihe Shi, Zhenshuai Yin, Haoyue Liu, Weixuan Wan, Xiaoying Tang
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:2607.15218v2 Announce Type: replace
Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become uns...
By Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu
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:2606. 11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code.
By Yitong Zhang, Shiteng Lu, Jia Li