GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models

Computer Science > Cryptography and Security [Submitted on 28 Mar 2026] GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models Md Jueal Mia, Joaquin Molto, Yanzhao Wu, M. Hadi Amini Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make SLMs suitable for resource-constrained and efficient deployment on edge devices. However, existing jailbreak defenses show limited robustness against heterogeneous attacks, largely due to an incomplete understanding of the internal representations across different layers of language models that facilitate jailbreak behaviors. In this paper, we conduct a comprehensive empirical study on 9 jailbreak attacks across 7 SLMs and 3 LLMs. Our analysis shows that SLMs remain highly vulnerable to malicious prompts that bypass safety alignment. We analyze hidden-layer activations across different layers and model architectures, revealing that different input types form distinguishable patterns in the internal representation space. Based on this observation, we propose GUARD-SLM, a lightweight token activation-based method that operates in the representation space to filter malicious prompts during inference while preserving benign ones. Our findings highlight robustness limitations across layers of language models and provide a practical direction for secure small language model deployment. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.28817 [cs.CR]   (or arXiv:2603.28817v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.28817 Focus to learn more Submission history From: Md Jueal Mia [view email] [v1] Sat, 28 Mar 2026 19:17:46 UTC (16,847 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)