AGSD patches make OpenVLA fail on all LIBERO suites; SARF fine-tuning cuts that failure rate from 100% to 28.6% average while preserving clean performance and improving real-robot success.
Synthesizing robust adversar- ial examples,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking
AGSD patches make OpenVLA fail on all LIBERO suites; SARF fine-tuning cuts that failure rate from 100% to 28.6% average while preserving clean performance and improving real-robot success.