Preprint
Aug 2026
Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking
Attention-Guided Semantic Disruption (AGSD), an Expectation-over-Transformation optimized printable patch that jointly concentrates action-to-vision attention on the patch and disrupts vision-language semantic alignment, yielding strong cross-task and cross-architecture transfer is proposed.
Jinquan Zhang, Dongfu Yin, Run Yang et al.
· 0 citations