TAKO demonstrates real-time adversarial takeover of robotic diffusion policies via reusable universal patches on visual inputs, achieving 100% success in steering attacker-chosen trajectories across multiple tasks, encoders, and diffusion methods.
Diffusion policy attacker: Craft- ing adversarial attacks for diffusion-based policies
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Modern imitation learning methods including Diffusion Policy and Implicit Behavior Cloning are highly vulnerable to universal adversarial perturbations, with successful black-box transfer attacks across algorithms.
citing papers explorer
-
Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies
TAKO demonstrates real-time adversarial takeover of robotic diffusion policies via reusable universal patches on visual inputs, achieving 100% success in steering attacker-chosen trajectories across multiple tasks, encoders, and diffusion methods.
-
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
Modern imitation learning methods including Diffusion Policy and Implicit Behavior Cloning are highly vulnerable to universal adversarial perturbations, with successful black-box transfer attacks across algorithms.