ACL Findings2025
Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
Sibo Yi, Tianshuo Cong, Xinlei He, Qi Li, Jiaxing Song
Abstract
Small language models (SLMs) have become increasingly prominent in the deployment on edge devices due to their high efficiency and low computational cost. While researchers continue to advance the capabilities of SLMs through innovative training strategies and model compression techniques, the security risks of SLMs have received considerably less attention compared to large language models (LLMs). To fill this gap, we provide a comprehensive empirical study to evaluate the security performance of 13 state-of-the-art SLMs under various jailbreak attacks. Our experiments demonstrate that most SLMs are quite susceptible to existing jailbreak attacks, while some of them are even vulnerable to direct harmful prompts. To address the safety concerns, we evaluate several representative defense methods and demonstrate their effectiveness in enhancing the security of SLMs. We further analyze the potential security degradation caused by different SLM techniques including architecture compression, quantization, knowledge distillation, and so on. We expect that our research can highlight the security challenges of SLMs and provide valuable insights to future work in developing more robust and secure SLMs.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness cites Language Models are Few-Shot Learners
- Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation cites Language Models are Few-Shot Learners
- Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Cited by top-tier papers1
Builds on19
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessTri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra et al.NeurIPS 2022 · 5,493 citations
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalMantas Mazeika, Long Phan, Xuwang Yin, Andy Zou et al.ICML 2024 · 1,031 citations
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei XiaoICLR 2024 · 722 citations
- Catastrophic Jailbreak of Open-source LLMs via Exploiting GenerationYangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li et al.ICLR 2024 · 481 citations
Related papers
- SPIRIT: Patching Speech Language Models against Jailbreak AttacksAmirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui, Hanan Aldarmaki et al.EMNLP 2025 · 3 citations
- Durable Quantization Conditioned Misalignment Attack on Large Language ModelsPeiran Dong, Haowei Li, Song GuoICLR 2025
- From LLMs to MLLMs: Exploring the Landscape of Multimodal JailbreakingSiyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu WeiEMNLP 2024 · 5 citations
- You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak DefenseWuyuao Mai, Geng Hong, Pei Chen, Xudong Pan et al.WWW 2025 · 9 citations
- Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language ModelsLang Gao, Jiahui Geng, Xiangliang Zhang, Preslav Nakov et al.ACL 2025
