典型文献
Exploiting natural language services:a polarity based black-box attack
文献摘要：
1 Introduction
Production input of Natural Language Processing(NLP)services can be be manipulated with malicious intent in order to lower the performance to a level that compromises the integrity of the service without any information on the under-lying model.The adversaries that perform word-level input perturbations in black-box settings first detect the"important"words,then perform noisy operations,such as replacement or deletion.Gao et al.[1]assigned word importance scores(temporal scores)calculated via querying the partial input for each individual sample.By this procedure,they queried the victim model on both the word score calculation and the perturbation stage,which potentially caused a big request-response overhead.In comparison,we only calculate the word importance scores(polarity score)once using an external dataset,and without querying the victim model.
文献关键词：
中图分类号：
作者姓名：
Fatma GUMUS;M.Fatih AMASYALI
作者机构：
Department of Computer Engineering,Yildiz Technical University,Istanbul 34220,Turkey;Department of Computer Engineering,Air Force Academy,National Defence University,Istanbul 34149,Turkey
文献出处：
引用格式：
[1]Fatma GUMUS;M.Fatih AMASYALI-.Exploiting natural language services:a polarity based black-box attack)[J].计算机科学前沿,2022(05):201-203
A类：
Production
B类：
Exploiting,natural,language,services,polarity,black,box,attack,Introduction,input,Natural,Language,Processing,NLP,can,be,manipulated,malicious,intent,order,lower,performance,level,that,compromises,integrity,without,any,information,under,lying,model,adversaries,perturbations,settings,first,detect,important,words,then,noisy,operations,such,replacement,deletion,Gao,assigned,importance,scores,temporal,calculated,via,querying,partial,each,individual,sample,By,this,procedure,they,queried,victim,both,calculation,stage,which,potentially,caused,big,request,response,overhead,comparison,only,once,using,external,dataset
AB值：
0.632664
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
