paper-with-me

Papers

Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective

2020-10-07 · ICCV 2021 10 · Philipp Benz, Chaoning Zhang, In So Kweon

Batch normalization (BN) has been widely used in modern deep neural networks (DNNs) due to improved convergence. BN is observed to increase the model accuracy while at the cost of adversarial robustness. There is an increasing interest in the ML community to understand the impact of BN on DNNs, especially related to the model robustness. This work attempts to understand the impact of BN on DNNs from a non-robust feature perspective. Straightforwardly, the improved accuracy can be attributed to the better utilization of useful features. It remains unclear whether BN mainly favors learning robust features (RFs) or non-robust features (NRFs). Our work presents empirical evidence that supports that BN shifts a model towards being more dependent on NRFs. To facilitate the analysis of such a feature robustness shift, we propose a framework for disentangling robust usefulness into robustness and usefulness. Extensive analysis under the proposed framework yields valuable insight on the DNN behavior regarding robustness, e.g. DNNs first mainly learn RFs and then NRFs. The insight that RFs transfer better than NRFs, further inspires simple techniques to strengthen transfer-based black-box attacks.

📄 PDF Abstract BibTeX arXiv:2010.03316

Code (1)

phibenz/adversarial_ml.research 공식 구현 pytorch

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Batch Normalization is a Cause of Adversarial Vulnerability

2019-05-06 · Angus Galloway, Anna Golubeva, Thomas Tanay, Medhat Moussa 외

Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low trainin…

Towards an Adversarially Robust Normalization Approach

2020-06-19 · Muhammad Awais, Fahad Shamshad, Sung-Ho Bae

Batch Normalization (BatchNorm) is effective for improving the performance and accelerating the training of deep neural networks. However, it has also shown to be a cause of adversarial vulnerability, i.e., networks with…

Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule

2022-01-28 · Naoki Sato, Hideaki Iiduka

Previous results have shown that a two time-scale update rule (TTUR) using different learning rates, such as different constant rates or different decaying rates, is useful for training generative adversarial networks (G…

On Fragile Features and Batch Normalization in Adversarial Training

2022-04-26 · Nils Philipp Walter, David Stutz, Bernt Schiele

Modern deep learning architecture utilize batch normalization (BN) to stabilize training and improve accuracy. It has been shown that the BN layers alone are surprisingly expressive. In the context of robustness against …

Adversarial Robustness

How to Use Dropout Correctly on Residual Networks with Batch Normalization

2023-02-13 · Bum Jun Kim, Hyeyeon Choi, Hyeonah Jang, Donggeon Lee 외

For the stable optimization of deep neural networks, regularization methods such as dropout and batch normalization have been used in various tasks. Nevertheless, the correct position to apply dropout has rarely been dis…

ClassificationFine-Grained Image ClassificationImage ClassificationPosition