Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices
This addresses a security problem for real-time applications like autonomous driving on edge devices, offering a novel defense against a new class of attacks.
The paper tackles latency attacks on object detectors for edge devices by proposing a background-attentive adversarial training method that accounts for hardware capabilities, restoring real-time processing from 13 FPS to 43 FPS on Jetson Orin NX while balancing clean and robust accuracy.
Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally known as misclassifying attacks. By targeting the real-time processing capability, a new class of latency attacks are reported recently. They exploit new attack surfaces in object detectors by creating a computational bottleneck in the post-processing module, that leads to cascading failure and puts the real-time downstream tasks at risks. In this work, we take an initial attempt to defend against this attack via background-attentive adversarial training that is also cognizant of the underlying hardware capabilities. We first draw system-level connections between latency attack and hardware capacity across heterogeneous GPU devices. Based on the particular adversarial behaviors, we utilize objectness loss as a proxy and build background attention into the adversarial training pipeline, and achieve a reasonable balance between clean and robust accuracy. The extensive experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS on Jetson Orin NX, with a better trade-off between the clean and robust accuracy.