Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models

Researchers have identified a specific internal SAE feature in VLA models that activates in the presence of adversarial patches, enabling a targeted, inference-time suppression defense that requires no model retraining. Critically, the defense must be applied conditionally—only when an attack is detected—as continuous suppression measurably degrades normal policy performance.

Defence Tech

Marines Rushing To Equip Amphibious Combat Vehicles With Anduril Pulsar-L Anti-Drone Jammers

By UAVHelpline Editorial · 5 min read

AI & Autonomy

FARE: The Forensic Watchdog That Catches AI Providers Swapping Certified Image Generators

By UAVHelpline Editorial · 5 min read