Related papers: Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces

URL: http://arxiv.org/abs/2012.14769v1
Date: Tue, 29 Dec 2020 14:28:07 GMT
Title: Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
Authors: Linyang Li, Yunfan Shao, Demin Song, Xipeng Qiu, Xuanjing Huang
Abstract summary: We propose a pre-train language model as the substitutes generator using sentence-pieces to craft adversarial examples in Chinese. The substitutions in the generated adversarial examples are not characters or words but textit'pieces', which are more natural to Chinese readers.
Score: 60.58900627906269
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in Chinese, such methods are not applicable since words in Chinese require segmentations first. In this paper, we propose a pre-train language model as the substitutes generator using sentence-pieces to craft adversarial examples in Chinese. The substitutions in the generated adversarial examples are not characters or words but \textit{'pieces'}, which are more natural to Chinese readers. Experiments results show that the generated adversarial samples can mislead strong target models and remain fluent and semantically preserved.

Related papers

Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning [69.35360098882606]
We introduce Click for controllable text generation, which needs no modification to the model architecture. It employs a contrastive loss on sequence likelihood, which fundamentally decreases the generation probability of negative samples. It also adopts a novel likelihood ranking-based strategy to construct contrastive samples from model generations.
arXiv Detail & Related papers (2023-06-06T01:56:44Z)
On The Ingredients of an Effective Zero-shot Semantic Parser [95.01623036661468]
We analyze zero-shot learning by paraphrasing training examples of canonical utterances and programs from a grammar. We propose bridging these gaps using improved grammars, stronger paraphrasers, and efficient learning methods. Our model achieves strong performance on two semantic parsing benchmarks (Scholar, Geo) with zero labeled data.
arXiv Detail & Related papers (2021-10-15T21:41:16Z)
Text Detoxification using Large Pre-trained Neural Models [57.72086777177844]
We present two novel unsupervised methods for eliminating toxicity in text. First method combines guidance of the generation process with small style-conditional language models. Second method uses BERT to replace toxic words with their non-offensive synonyms.
arXiv Detail & Related papers (2021-09-18T11:55:32Z)
From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation [14.360808219541752]
We study a new application for text generation -- idiomatic sentence generation. We propose a novel approach for this task, which retrieves the appropriate idiom for a given literal sentence. We generate the idiomatic sentence by using a neural model to combine the retrieved idiom and the remainder of the sentence.
arXiv Detail & Related papers (2021-04-13T22:57:25Z)
AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text [39.09728700494304]
We present AdvExpander, a method that crafts new adversarial examples by expanding text. We first utilize linguistic rules to determine which constituents to expand. We then expand each constituent by inserting an adversarial modifier searched from a CVAE-based generative model.
arXiv Detail & Related papers (2020-12-18T13:50:17Z)
Contextualized Perturbation for Textual Adversarial Attack [56.370304308573274]
Adversarial examples expose the vulnerabilities of natural language processing (NLP) models. This paper presents CLARE, a ContextuaLized AdversaRial Example generation model that produces fluent and grammatical outputs.
arXiv Detail & Related papers (2020-09-16T06:53:15Z)
Don't Change Me! User-Controllable Selective Paraphrase Generation [45.0436584774495]
In paraphrase generation, source sentences often contain phrases that should not be altered. Our solution is to provide the user with explicit tags that can be placed around any arbitrary segment of text to mean "don't change me!" The contribution of this work is a novel data generation technique using distant supervision.
arXiv Detail & Related papers (2020-08-21T03:31:50Z)
2kenize: Tying Subword Sequences for Chinese Script Conversion [54.33749520569979]
We propose a model that can disambiguate between mappings and convert between the two scripts. Our proposed method outperforms previous Chinese Character conversion approaches by 6 points in accuracy.
arXiv Detail & Related papers (2020-05-07T10:53:05Z)
BAE: BERT-based Adversarial Examples for Text Classification [9.188318506016898]
We present BAE, a black box attack for generating adversarial examples using contextual perturbations from a BERT masked language model. We show that BAE performs a stronger attack, in addition to generating adversarial examples with improved grammaticality and semantic coherence as compared to prior work.
arXiv Detail & Related papers (2020-04-04T16:25:48Z)
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models [41.85006993382117]
We propose an end to end solution to efficiently generate adversarial texts from scratch using generative models. Specifically, we train a conditional variational autoencoder with an additional adversarial loss to guide the generation of adversarial examples. To improve the validity of adversarial texts, we utilize discrimators and the training framework of generative adversarial networks.
arXiv Detail & Related papers (2020-03-10T03:21:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.