paper-with-me

Papers

Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

2021-03-07 · Jinyu Tian, Jiantao Zhou, Yuanman Li, Jia Duan

Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. This phenomenon motivates us to design another classifier (called dual classifier) with transformed decision boundary, which can be collaboratively used with the original classifier (called primal classifier) to detect AEs, by virtue of the sensitivity inconsistency. When comparing with the state-of-the-art algorithms based on Local Intrinsic Dimensionality (LID), Mahalanobis Distance (MD), and Feature Squeezing (FS), our proposed Sensitivity Inconsistency Detector (SID) achieves improved AE detection performance and superior generalization capabilities, especially in the challenging cases where the adversarial perturbation levels are small. Intensive experimental results on ResNet and VGG validate the superiority of the proposed SID.

📄 PDF Abstract BibTeX arXiv:2103.04302

Code (1)

TooTouch/SID pytorch

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Average Pooling 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Detecting Adversarial Examples by Additional Evidence from Noise Domain

2021-01-01 · Song Gao, Shui Yu, Shaowen Yao

Deep neural networks are widely adopted powerful tools for perceptual tasks. However, recent research indicated that they are easily fooled by adversarial examples, which are produced by adding imperceptible adversarial …

Steganalysis

Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?

2020-06-26 · Kaidi Jin, Tianwei Zhang, Chao Shen, Yufei Chen 외

Deep Neural Networks are well known to be vulnerable to adversarial attacks and backdoor attacks, where minor modifications on the input are able to mislead the models to give wrong results. Although defenses against adv…

Adversarial DefenseBackdoor Attack

Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks

2021-01-05 · Rachel Sterneck, Abhishek Moitra, Priyadarshini Panda

Neural networks have achieved remarkable performance in computer vision, however they are vulnerable to adversarial examples. Adversarial examples are inputs that have been carefully perturbed to fool classifier networks…

QuantizationSensitivity

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks

2017-04-04 · Network and Distributed System Security Symposium 2018 2 · Weilin Xu, David Evans, Yanjun Qi

Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. P…

Conformal Shield: A Novel Adversarial Attack Detection Framework for Automatic Modulation Classification

2024-02-27 · Tailai Wen, Da Ke, Xiang Wang, Zhitao Huang

Deep learning algorithms have become an essential component in the field of cognitive radio, especially playing a pivotal role in automatic modulation classification. However, Deep learning also present risks and vulnera…

Adversarial AttackAdversarial Attack DetectionClassificationDeep Learning+1