Understanding and Quantifying Adversarial Examples Existence in Linear Classification
State-of-art deep neural networks (DNN) are vulnerable to attacks by adversarial examples: a carefully designed small perturbation to the input, that is imperceptible to human, can mislead DNN. To understand the root cause of adversarial examples, we quantify the probability of adversarial example existence for linear classifiers. Previous mathematical definition of adversarial examples only involves the overall perturbation amount, and we propose a more practical relevant definition of strong adversarial examples that separately limits the perturbation along the signal direction also. We show that linear classifiers can be made robust to strong adversarial examples attack in cases where no adversarial robust linear classifiers exist under the previous definition. The quantitative formulas are confirmed by numerical experiments using a linear support vector machine (SVM) classifier. The results suggest that designing general strong-adversarial-robust learning systems is feasible but only through incorporating human knowledge of the underlying classification problem.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Quantifying and Understanding Adversarial Examples in Discrete Input Spaces
Modern classification algorithms are susceptible to adversarial examples--perturbations to inputs that cause the algorithm to produce undesirable behavior. In this work, we seek to understand and extend adversarial examp…
AttributeSentiment AnalysisAdversarial Examples for Natural Language Classification Problems
Modern machine learning algorithms are often susceptible to adversarial examples — maliciously crafted inputs that are undetectable by humans but that fool the algorithm into producing undesirable behavior. In this work,…
BIG-bench Machine LearningClassificationFake News DetectionGeneral Classification+2Gradient-Free Adversarial Attacks for Bayesian Neural Networks
The existence of adversarial examples underscores the importance of understanding the robustness of machine learning models. Bayesian neural networks (BNNs), due to their calibrated uncertainty, have been shown to posses…
Adversarial RobustnessBayesian InferenceUnderstanding Adversarial Robustness Against On-manifold Adversarial Examples
Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of th…
Adversarial RobustnessDelving into Transferable Adversarial Examples and Black-box Attacks
An intriguing property of deep neural networks is the existence of adversarial examples, which can transfer among different architectures. These transferable adversarial examples may severely hinder deep neural network-b…
Adversarial AttackAdversarial Defenseimage-classificationImage Classification