TBT: Targeted Neural Network Attack with Bit Trojan

by   Adnan Siraj Rakin, et al.

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively infect the model during the training phase and get activated only through specific input patterns (i.e, trigger) during inference. However, in this work, for the first time, we propose a novel Targeted Bit Trojan(TBT), which eliminates the need for model re-training to insert the targeted Trojan. Our algorithm efficiently generates a trigger specifically designed to locate certain vulnerable bits of DNN weights stored in main memory (i.e., DRAM). The objective is that once the attacker flips these vulnerable bits, the network still operates with normal inference accuracy. However, when the attacker activates the trigger embedded with input images, the network classifies all the inputs to a certain target class. We demonstrate that flipping only several vulnerable bits founded by our method, using available bit-flip techniques (i.e, row-hammer), can transform a fully functional DNN model into a Trojan infected model. We perform extensive experiments of CIFAR-10, SVHN and ImageNet datasets on both VGG-16 and Resnet-18 architectures. Our proposed TBT could classify 93 bit-flips out of 88 million weight bits on Resnet-18 for CIFAR10 dataset.


page 1

page 2

page 3

page 4


Bit-Flip Attack: Crushing Neural Network withProgressive Bit Search

Several important security issues of Deep Neural Network (DNN) have been...

DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips

Security of machine learning is increasingly becoming a major concern du...

TrojViT: Trojan Insertion in Vision Transformers

Vision Transformers (ViTs) have demonstrated the state-of-the-art perfor...

HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks

We propose HASHTAG, the first framework that enables high-accuracy detec...

An Optimization Perspective on Realizing Backdoor Injection Attacks on Deep Neural Networks in Hardware

State-of-the-art deep neural networks (DNNs) have been proven to be vuln...

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

To explore the vulnerability of deep neural networks (DNNs), many attack...

Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks

Bit-flip attacks (BFAs) have attracted substantial attention recently, i...

Please sign up or login with your details

Forgot password? Click here to reset