# CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation

arXiv: https://arxiv.org/abs/2504.13201 · HTML: https://mlsanity.com/paper/2504.13201/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- First posted on arXiv 15 Apr 2025.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Built on by (most cited first, 4 of 4)

- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task](https://mlsanity.com/paper/2603.14367/) (2026)
- [Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2609.27847/) (2026)
- [Multimodal Safety Evaluation Should Measure Controllability Beyond Classification](https://mlsanity.com/paper/2610.06452/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores inference-time defenses, existing methods rely on static interventions on intermediate representations, which often degrade generation quality and impair adherence to task instructions, reducing system usability in EI settings. We propose a dynamic defense framework. For each EI inference request, we dynamically construct a task-specific safety-semantic subspace, project its hidden state to the most relevant direction, and apply SLERP rotation for adaptive safety control. At comparable defense success rates, our method preserves generation quality, improves usability, reduces tuning cost, and strengthens robustness in EI scenarios.