Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA

Abstract

The wide deployment of Deep Neural Networks (DNN) in high-performance cloud computing platforms brought to light multi-tenant cloud field-programmable gate arrays (FPGA) as a popular choice of accelerator to boost performance due to its hardware reprogramming flexibility. Such a multi-tenant FPGA setup for DNN acceleration potentially exposes DNN interference tasks under severe threat from malicious users. This work, to the best of our knowledge, is the first to explore DNN model vulnerabilities in multi-tenant FPGAs. We propose a novel adversarial attack framework: Deep-Dup, in which the adversarial tenant can inject adversarial faults to the DNN model in the victim tenant of FPGA. Specifically, she can aggressively overload the shared power distribution system of FPGA with malicious power-plundering circuits, achieving adversarial weight duplication (AWD) hardware attack that duplicates certain DNN weight packages during data transmission between off-chip memory and on-chip buffer, to hijack the DNN function of the victim tenant. Further, to identify the most vulnerable DNN weight packages for a given malicious objective, we propose a generic vulnerable weight package searching algorithm, called Progressive Differential Evolution Search (P-DES), which is, for the first time, adaptive to both deep learning white-box and black-box attack models. The proposed Deep-Dup is experimentally validated in a developed multi-tenant FPGA prototype, for two popular deep learning applications, i.e., Object Detection and Image Classification. Successful attacks are demonstrated in six popular DNN architectures (e.g., YOLOv2, ResNet-50, MobileNet, etc.)

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Achieving Human Parity in Conversational Speech Recognition
• Is feature selection secure against training data poisoning?
• Simple Black-Box Adversarial Perturbations for Deep Networks
• Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
• DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA
• T-BFA: Targeted Bit-Flip Adversarial Weight Attack
• DeepLaser: Practical Fault Attack on Deep Neural Networks
• DNNExplorer: A Framework for Modeling and Exploring a Novel Paradigm of FPGA-based DNN Accelerator

Cited by in corpus (1)

• DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA