GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models
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 differe
Record details
Published: 28 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Military & security
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv · 19 March 2026
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
arXiv · 9 April 2026
SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
arXiv · 16 March 2026
Directional Embedding Smoothing for Robust Vision Language Models
arXiv · 16 March 2026
AI Integrity: A New Paradigm for Verifiable AI Governance
arXiv · 13 April 2026
Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking
arXiv · 7 March 2026
How to cite this record
ethics.ai (28 March 2026), “GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models,” evidence record 6636, https://ethics.ai/record/6636 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.