paper-with-me

홈 › Papers

The Adversarial Attack and Detection under the Fisher Information Metric

2018-10-09 · Chenxiao Zhao, P. Thomas Fletcher, Mixue Yu, Yaxin Peng, Guixu Zhang, Chaomin Shen

Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information geometry, we provide a reasonable explanation for the vulnerability of deep learning models. By considering the data space as a non-linear space with the Fisher information metric induced from a neural network, we first propose an adversarial attack algorithm termed one-step spectral attack (OSSA). The method is described by a constrained quadratic form of the Fisher information matrix, where the optimal adversarial perturbation is given by the first eigenvector, and the model vulnerability is reflected by the eigenvalues. The larger an eigenvalue is, the more vulnerable the model is to be attacked by the corresponding eigenvector. Taking advantage of the property, we also propose an adversarial detection method with the eigenvalues serving as characteristics. Both our attack and detection algorithms are numerically optimized to work efficiently on large datasets. Our evaluations show superior performance compared with other methods, implying that the Fisher information is a promising approach to investigate the adversarial attacks and defenses.

📄 PDF Abstract BibTeX arXiv:1810.03806

Code (1)

eliot-tron/curvnetattack pytorch

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Inspecting adversarial examples using the Fisher information

2019-09-12 · Jörg Martin, Clemens Elster

Adversarial examples are slight perturbations that are designed to fool artificial neural networks when fed as an input. In this work the usability of the Fisher information for the detection of such adversarial attacks …

Detection based Defense against Adversarial Examples from the Steganalysis Point of View

2018-06-21 · CVPR 2019 6 · Jiayang Liu, Weiming Zhang, Yiwei Zhang, Dongdong Hou 외

Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically mislead…

Steganalysis

Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix

2019-09-13 · Chaomin Shen, Yaxin Peng, Guixu Zhang, Jinsong Fan

We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on the rationale of adversarial examples. …

Adversarial DefenseTraffic Sign Recognition

Adversarial attacks on neural networks through canonical Riemannian foliations

2022-03-02 · Eliot Tron, Nicolas Couellan, Stéphane Puechmorel

Deep learning models are known to be vulnerable to adversarial attacks. Adversarial learning is therefore becoming a crucial task. We propose a new vision on neural network robustness using Riemannian geometry and foliat…

Adversarial Attack

ScAR: Scaling Adversarial Robustness for LiDAR Object Detection

2023-12-05 · Xiaohu Lu, Hayder Radha

The adversarial robustness of a model is its ability to resist adversarial attacks in the form of small perturbations to input data. Universal adversarial attack methods such as Fast Sign Gradient Method (FSGM) and Proje…

3D Object DetectionAdversarial AttackAdversarial RobustnessObject+2