@inproceedings{zhou-etal-2025-hidden,
    title = "The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1",
    author = "Zhou, Kaiwen  and
      Liu, Chengzhi  and
      Zhao, Xuandong  and
      Jangam, Shreedhar  and
      Srinivasa, Jayanth  and
      Liu, Gaowen  and
      Song, Dawn  and
      Wang, Xin Eric",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-long.173/",
    pages = "3250--3265",
    ISBN = "979-8-89176-298-5",
    abstract = "The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models (LLMs). However, their enhanced capabilities, combined with the open-source access of models like DeepSeek-R1, raise serious safety concerns, particularly regarding their potential for misuse. In this work, we present a comprehensive safety assessment of these reasoning models, leveraging established safety benchmarks to evaluate their compliance with safety regulations. Furthermore, we investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications. Through our multi-faceted analysis, we uncover four key findings: (1) There is a significant safety gap between the open-source reasoning models and the o3-mini model, on both safety benchmark and attack, suggesting more safety effort on open LRMs is needed. (2) The distilled reasoning model shows poorer safety performance compared to its safety-aligned base models. (3) The stronger the model{'}s reasoning ability, the greater the potential harm it may cause when answering unsafe questions. (4) The thinking process in R1 models poses greater safety concerns than their final answers. Our study provides insights into the security implications of reasoning models and highlights the need for further advancements in R1 models' safety to close the gap."
}