Article

Detect and Suppress: A Mechanistic Defense Against Adversarial Patches on VLA Models

The authors use a sparse autoencoder (SAE) to analyze the internal representations of a VLA model, identify a feature whose activation strongly correlates with the presence of adversarial patches, and suppress that feature at inference time only when a linear probe detects an attack, thereby improving robustness without fine-tuning the VLA. In adversarial patch attack tests on LIBERO-10, conditional intervention improved the success rate under intermittent attacks, whereas continuously applying the same intervention substantially degraded policy performance.

Part of the event: SAE Feature Suppression Defense Against VLA Adversarial Patches

This page provides a summary and source link only.