Fault-tolerant deep learning inference on CPU-GPU integrated edge devices with TEEs

CPU-GPU integrated edge devices and deep learning algorithms have received significant progress in recent years, leading to increasingly widespread application of edge intelligence. However, deep learning inference on these edge devices is vulnerable to Fault Injection Attacks (FIAs) that can modify...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Future generation computer systems Jg. 161; S. 404 - 414
Hauptverfasser: Xu, Hongjian, Liao, Longlong, Liu, Xinqi, Chen, Shuguang, Chen, Jianguo, Liang, Zhixuan, Yu, Yuanlong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.12.2024
Schlagworte:
CPU-GPU integrated edge device
Deep learning
Fault injection attack
Fault-tolerant inference
Trusted Execution Environment
Deep learning
Fault-tolerant inference
Trusted Execution Environment
Fault injection attack
CPU-GPU integrated edge device
ISSN:0167-739X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:CPU-GPU integrated edge devices and deep learning algorithms have received significant progress in recent years, leading to increasingly widespread application of edge intelligence. However, deep learning inference on these edge devices is vulnerable to Fault Injection Attacks (FIAs) that can modify device memory or execute instructions with errors. We propose DarkneTF, a Fault-Tolerant (FT) deep learning inference framework for CPU-GPU integrated edge devices, to ensure the correctness of model inference results by detecting the threat of FIAs. DarkneTF introduces algorithm-based verification to implement the FT deep learning inference. The verification process involves verifying the integrity of model weights and validating the correctness of time-intensive calculations, such as convolutions. We improve the Freivalds algorithm to enhance the ability to detect tiny perturbations by strengthening randomization. As the verification process is also susceptible to FIAs, DarkneTF offloads the verification process into Trusted Execution Environments (TEEs). This scheme ensures the verification process’s security and allows for accelerated model inference using the integrated GPUs. Experimental results show that GPU-accelerated FT inference on HiKey 960 achieves notable speedups ranging from 3.46x to 5.57x compared to FT inference on a standalone CPU. The extra memory overhead incurred FT inference remains at an exceedingly low level, with a range of 0.46% to 10.22%. The round-off error of the improved Freivalds algorithm is below 2.50×10−4, and the accuracy of detecting FIAs is above 92.73%. •DarkneTF detects fault injection attacks for deep learning inference.•DarkneTF uses the TEE-enabled verification to protect deep learning inference.•DarkneTF enables to accelerate fault-tolerant inference with the integrated GPU.
ISSN:0167-739X
DOI:10.1016/j.future.2024.07.027