Universal Adversarial Perturbation for Text Classification
Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probability. Unlike images on which a single fixed-size adversarial perturbation can be found, text is of variable length, so we define the "universality" as "token-agnostic", where a single perturbation is applied to each token, resulting in different perturbations of flexible sizes at the sequence level. We propose an algorithm to compute universal adversarial perturbations, and show that the state-of-the-art deep neural networks are highly vulnerable to them, even though they keep the neighborhood of tokens mostly preserved. We also show how to use these adversarial perturbations to generate adversarial text samples. The surprising existence of universal "token-agnostic" adversarial perturbations may reveal important properties of a text classifier.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial TextClassificationGeneral Classificationtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Universal adversarial perturbations for multiple classification tasks with quantum classifiers
Quantum adversarial machine learning is an emerging field that studies the vulnerability of quantum learning systems against adversarial perturbations and develops possible defense strategies. Quantum universal adversari…
Continual LearningQuantum Machine LearningLearning Universal Adversarial Perturbations with Generative Models
Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that …
Graph ClassificationDefending Against Universal Perturbations With Shared Adversarial Training
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image class…
image-classificationImage ClassificationSemantic SegmentationTowards Imperceptible Universal Attacks on Texture Recognition
Although deep neural networks (DNNs) have been shown to be susceptible to image-agnostic adversarial attacks on natural image classification problems, the effects of such attacks on DNN-based texture recognition have yet…
image-classificationImage ClassificationUniversal Adversarial Perturbations: Efficiency on a small image dataset
Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has show…
image-classificationImage Classification