基于多擾動策略的中文對抗樣本生成方法

打開文本圖片集

Chinese adversarial example generation method based on multi-disturbance strategy

Wang Chundong1，2，Zhu Wenying1，2，Lin Hao1，2（1.Scholofuee&inUesitna；NlEforComputer VirusPrevention&Control Technology，Tianjin 3Oo384，China）

Abstract：Toaddress thevulnerabilityofdeepneuralnetworkstoadversarialsamplesandthelackofhigh-qualityadversarial samples inthe Chinese context，the method introduced a new Chinese adversarial sample generation method named CMDS.In thekeywordselectionstage，theScore functionusedidentifiespositions whereperturbationscouldbeadded efectively，nsuring theadversarialsamples werebothreadableanddificulttodetect.Duringtheadversarialsamplegeneration phase，themethod fullexploited characteristicsunique to Chinese，consideringaspectssuchas character shape，meaning，andregion-specific homophones.Variousperturbationstrategies，includingsimilarcharacters，syonyms，homophones，andwordoderdisuption were employedalongwitha multi-priorityperturbation strategy to generateadversarial samples.Finally，aperturbationrate thresholdcontroledteoutput，eliminatingsamplesthatdiferedtoogreatlyfromteriginaltext.Folowingthis，asrsofexperimentscompared CMDS with baselinemethods to exploretheimpact of perturbation threshold sizes，involved humanevaluations，andconductedreal-worldattack tests.These experimentsconfimtheefectivenessandtransferabilityofCMDSinenhancing model securityResultsshowthat CMDS surpassesbaseline methods in terms of attck successratebyupto36.9 percentagepointsandimproves modelsecuritybymore than3Opercentagepoints.The generatedadversarialsamplesareofhighquality and demonstrate strong generalizability.

Key words：deep neural network；natural language procesing（NLP）；Chineseadversarial example；multi-disturbance

0引言

近些年來，人工智能技術(shù)快速發(fā)展使其在計算機(jī)視覺[1]自然語言處理[2]、數(shù)據(jù)挖掘[3]、機(jī)器翻譯[4]等領(lǐng)域有著重要的研究和應(yīng)用，但深度神經(jīng)網(wǎng)絡(luò)的可解釋性相對較差[5]，難以解釋其最終的輸出結(jié)果。（剩余18252字）