Data-free Backdoor Removal based on Channel Lipschitzness

by   Runkai Zheng, et al.

Recent studies have shown that Deep Neural Networks (DNNs) are vulnerable to the backdoor attacks, which leads to malicious behaviors of DNNs when specific triggers are attached to the input images. It was further demonstrated that the infected DNNs possess a collection of channels, which are more sensitive to the backdoor triggers compared with normal channels. Pruning these channels was then shown to be effective in mitigating the backdoor behaviors. To locate those channels, it is natural to consider their Lipschitzness, which measures their sensitivity against worst-case perturbations on the inputs. In this work, we introduce a novel concept called Channel Lipschitz Constant (CLC), which is defined as the Lipschitz constant of the mapping from the input images to the output of each channel. Then we provide empirical evidences to show the strong correlation between an Upper bound of the CLC (UCLC) and the trigger-activated change on the channel activation. Since UCLC can be directly calculated from the weight matrices, we can detect the potential backdoor channels in a data-free manner, and do simple pruning on the infected DNN to repair the model. The proposed Channel Lipschitzness based Pruning (CLP) method is super fast, simple, data-free and robust to the choice of the pruning threshold. Extensive experiments are conducted to evaluate the efficiency and effectiveness of CLP, which achieves state-of-the-art results among the mainstream defense methods even without any data. Source codes are available at


page 1

page 2

page 3

page 4


Structural Watermarking to Deep Neural Networks via Network Channel Pruning

In order to protect the intellectual property (IP) of deep neural networ...

Channel Pruning via Automatic Structure Search

Channel pruning is among the predominant approaches to compress deep neu...

EZCrop: Energy-Zoned Channels for Robust Output Pruning

Recent results have revealed an interesting observation in a trained con...

Channel Pruning Guided by Spatial and Channel Attention for DNNs in Intelligent Edge Computing

Deep Neural Networks (DNNs) have achieved remarkable success in many com...

Network Pruning via Feature Shift Minimization

Channel pruning is widely used to reduce the complexity of deep network ...

Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining

A challenge of channel pruning is designing efficient and effective crit...

RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging

Pruning Deep Neural Networks (DNNs) is a prominent field of study in the...

Please sign up or login with your details

Forgot password? Click here to reset