2 papers
cs.LG2026
N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator
Zheyu Lin, Jirui Yang, Yukui Qiu +3
Evaluating the safety robustness of LLMs is critical for their deployment. However, mainstream Red Teaming methods rely on online generation and black-box output analysis. These ap…
cs.CR2026
CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation
Jirui Yang, Zheyu Lin, Zhihui Lu +6
Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerabil…