Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

Quantized Vision-Language-Action VLA models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to $0%$, while hundreds of random flips are harmless. Across...

SoK: Security and Privacy of Foundation-Model-Powered Robots

Foundation models are reshaping robotics by enabling robots to interpret open-ended instructions, reason over multimodal contexts, and operate in complex, open-world environments. However, their integration also introduces security and privacy S&P risks that extend beyond the FMs themselves to...

Vulnerability in Robots Can Lead To Costly Ransomware Attacks

CANCUN, Mexico – A vulnerability in Softbank Robotics’ NAO and Pepper robots can lead to costly ransomware attacks that could cause robots deployed in businesses to stop working, curse at customers, or even perform violent movements. The vulnerability was disclosed at Kaspersky Lab’s Security...