paper-with-me

Papers

Universal Adversarial Perturbation for Text Classification

2019-10-10 · Hang Gao, Tim Oates

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.

📄 PDF Abstract BibTeX arXiv:1910.04618

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial TextClassificationGeneral Classificationtext-classificationText Classification

Similar Papers 제목 키워드 기반

Universal adversarial perturbations for multiple classification tasks with quantum classifiers

2023-06-21 · Yun-Zhong Qiu

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 Learning

Learning Universal Adversarial Perturbations with Generative Models

2017-08-17 · Jamie Hayes, George Danezis

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 Classification

Defending Against Universal Perturbations With Shared Adversarial Training

2018-12-10 · ICCV 2019 10 · Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen

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 Segmentation

Towards Imperceptible Universal Attacks on Texture Recognition

2020-11-24 · Yingpeng Deng, Lina J. Karam

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 Classification

Universal Adversarial Perturbations: Efficiency on a small image dataset

2022-10-10 · Waris Radji

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