SoK: Efficiency Robustness of Dynamic Deep Learning Systems
No ratings
Presented at USENIX Security 2025 by
Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resource-constrained environments such as mobile and IoT devices. To address efficiency challenges, Dynamic Deep Learning Systems (DDLSs) adapt inference computation based on input complexity, reducing overhead. While this dynamic behavior improves efficiency, such behavior introduces new attack surfaces. In particular, efficiency adversarial attacks exploit these dynamic mechanisms to degrade system performance.