面向中文用户评论的自动化众包攻击方法

doi:10.11959/j.issn.1000-436x.2019149

Abstract

Abstract:

The text-oriented automated crowdturfing attack has a series of features such as low attack cost and strong concealment.This kind of attack can automatically generate a large number of fake reviews,with harmful effect on the healthy development of the user review community.In recent years,researchers have found that text-oriented crowdturfing attacks for the English review community,but there was few research work on automated crowdsourcing attacks in the Chinese review community.A Chinese character embedding LSTM model was proposed to automatically generate Chinese reviews with the aim of antomated crowdturfing attacks,which model trained by a combination with Chinese character embedding network,LSTM network and softmax dense network,and a temperature parameter T was designed to construct the attack model.In the experiment,more than 50 000 real user reviews were crawled from Taobao's online review platform to verify the effectiveness of the attack method.Experimental results show that the generated fake reviews can effectively fool linguistics-based classification detection approach and texts plagiarism detection approach.Besides,the massive manually evaluation experiments also demonstrate that the generated reviews with the proposed attack approach perform well in reality and diversity.

Key words: user review community, automated crowdturfing attack, Chinese character embedding network, LSTM

CLC Number:

TP309.1

WANG Li’na,GUO Xiaodong,WANG Run. Automated crowdturfing attack in Chinese user reviews[J]. Journal on Communications, 2019, 40(6): 1-13.

Figures/Tables 13

References 40

[1]	AKOGLU L , CHANDY R , FALOUTSOS C . Opinion fraud detectionin online reviews by network effects[C]// The International AAAI Conference on Weblogs and Social Media. AAAI, 2013: 1-12.
[2]	LACKERMAIR G , KAILER D , KANMAZ K . Importance of online product reviews from a consumer's perspective[J]. Advances in Economics and Business, 2013,1(1): 1-5.
[3]	金立印 . 网络口碑信息对消费者购买决策的影响：一个实验研究[J]. 经济管理, 2007(22): 36-42.
	JIN L Y . The impact of internet word-of-mouth information on consumers' purchase decisions:an experimental study[J]. Economic Management, 2007(22): 36-42.
[4]	LUCA M , ZERVAS G . Fake it till you make it:reputation,competition,and yelp review fraud[J]. Management Science, 2016,62(12): 3412-3427.
[5]	LIPSMAN A , . Online consumer-generated reviews have significant impact on offline purchase behavior[C]// Industry Analysis,comScore Inc. 2007: 2-8.
[6]	JINDAL N , LIU B . Opinion spam and analysis[C]// International Conference on Web Search and Data Mining. ACM, 2008: 219-230.
[7]	WANG G , WILSON C , ZHAO X ,et al. Serf and turf:crowdturfing for fun and profit[C]// The International Conference on World Wide Web. ACM, 2012: 679-688.
[8]	LEE K , WEBB S , GE H . Characterizing and automatically detecting crowdturfing in Fiverr and Twitter[J]. Social Network Analysis and Mining, 2015,5(1): 1-6.
[9]	孟美任, 丁晟春 . 虚假商品评论信息发布者行为动机分析[J]. 情报科学, 2013(10): 100-104.
	MENG M R , DING S C . Analysis of behavioral motivation of publishers of false commodity commentary information[J]. Information Science, 2013(10): 100-104.
[10]	YAO Y , VISWANATH B , CRYAN J ,et al. Automated crowdturfing attacks and defenses in online review systems[J]. ACM, 2017: 1143-1158.
[11]	BARTOLI A , LORENZO A D , MEDVET E ,et al. "Best dinner ever!!!":automatic generation of restaurant reviews with LSTM-RNN[C]// IEEE/WIC/ACM International Conference on Web Intelligence. IEEE, 2017: 721-724.
[12]	MIKOLOV T . Statistical language models based on neural networks[M]. Mountain View,Presentation at Google, 2012: 2-80.
[13]	WEN T H , GASIC M , MRKSIC N ,et al. Semantically conditioned LSTM-based natural language generation for spoken dialogue systems[J]. Computer Science, 2015: 1711-1721.
[14]	ZHANG Q , WANG D Y , VOELKER G M . DSpin:detecting automatically spun content on the web[C]// The Network and Distributed System Security Symposium. 2014: 1-11.
[15]	杨钊, 陶大鹏, 张树业 ,等. 大数据下的基于深度神经网的相似汉字识别[J]. 通信学报, 2014,35(9): 184-189.
	YANG Z , TAO D P , ZHANG S Y ,et al. Similarity of Chinese character recognition based on deep neural network under big data[J]. Journal on Communications, 2014,35(9): 184-189.
[16]	张蕾, 章毅 . 大数据分析的无限深度神经网络方法[J]. 计算机研究与发展, 2016,53(1): 68-79.
	ZHANG L , ZHANG Y . Infinite depth neural network method for big data analysis[J]. Journal of Computer Research and Development, 2016,53(1): 68-79.
[17]	MURPHY K P . Machine learning:a probabilistic perspective[J]. MIT press, 2012,27(2): 62-63.
[18]	TAI Y , HE H , ZHANG W Z ,et al. Automatic generation of review content in specific domain of social network based on RNN[C]// IEEE International Conference on Data Science in Cyberspace. IEEE, 2018: 601-608.
[19]	AULI M , GALLEY M , QUIRK C ,et al. Joint language and translation modeling with recurrent neural networks[C]// The 2013 Conference on Empirical Methods in Natural Language Processing. 2013: 1044-1054.
[20]	KANNAN A , . Smart reply:automated response suggestion for email[C]// The ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 955-964.
[21]	KARPATHY A , FEI-FEI L . Deep visual-semantic alignments for generating image descriptions[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3128-3137.
[22]	SERBAN IV , SORDONI A , BENGIO Y ,et al. Hierarchical neural network generative models for movie dialogues[J]. Cornell University,arXiv:1507,04808.
[23]	SHANG L , LU Z , LI H . Neural responding machine for short-text conversation[C]// The Annual Meeting of the Association for Computational Linguistics and The International Joint Conference on Natural Language Processing,Association for Computational Linguistics. 2015(1): 1577-1586.
[24]	SUN Y , LIN L , TANG D ,et al. Radical-enhanced Chinese character embedding[J]. Lecture Notes in Computer Science, 2014: 279-286.
[25]	Graves A . Generating Sequences With Recurrent Neural Networks[J]. Cornell University,arXiv:1308,0850.
[26]	LEBRET R , GRANGIER D , AULI M . Neural text generation from structured data with application to the biography domain[C]// The Conference on Empirical Methods in Natural Language Processing. 2016: 1203-1213.
[27]	MIKOLOV T , SUTSKEVER I , CHEN K ,et al. Distributed representations of words and phrases and their compositionality[J]. Advances in Neural Information Processing Systems, 2013(26): 3111-3119.
[28]	曾谁飞, 张笑燕, 杜晓峰 ,等. 基于神经网络的文本表示模型新方法[J]. 通信学报, 2017,38(4): 86-98.
	ZENG S F , ZHANG X Y , DU X F ,et al. A new method of text representation model based on neural network[J]. Journal on Communications, 2017,38(4): 86-98.
[29]	WANG X , LIU Y , CHENGJIE S U ,et al. Predicting polarities of tweets by composing word embeddings with long short-term memory[C]// The Annual Meeting of The Association for Computational Linguistics,The International Joint Conference on Natural Language Processing. 2015(1): 1343-1353.
[30]	SUTSKEVER I , VINYALS O , LE Q V . Sequence to sequence learning with neural networks[J]. In Advances in Neural Information Processing Systems, 2014: 3104-3112.
[31]	XU K , BA J , KIROS R ,et al. Show,attend and tell:neural imagecaption generation with visual attention[C]// International Conference on Machine Learning. 2015: 2048-2057.
[32]	RUSH A M , CHOPRA S , WESTON J . A neural attention model for abstractive sentence summarization[C]// The Conference on Empirical Methods in Natural Language Processing. 2015: 379-389.
[33]	CRAWFORD M , KHOSHGOFTAAR T M , PRUSA J D ,et al. Survey of review spam detection using machine learning techniques[J]. Journal of Big Data, 2015,2(1): 1-24.
[34]	李璐旸, 秦兵, 刘挺 . 虚假评论检测研究综述[J]. 计算机学报, 2018,41(4): 946-968.
	LI W , QIN B , LIU T . A review of false comment detection research[J]. Chinese Journal of Computers, 2018,41(4): 946-968.
[35]	OTT M , CHOI Y , CARDIE C ,et al. Finding deceptive opinion spam by any stretch of the imagination[C]// The Annual Meeting of the Association for Computational Linguistics:Human Language Technologies,Association for Computational Linguistics. 2011(1): 309-319.
[36]	LI J , OTT M , CARDIE C ,et al. Towards a general rule for identifying deceptive opinion spam[C]// The Annual Meeting of the Association for Computational Linguistics,Association for Computational Linguistics. 2014(1): 1566-1576.
[37]	CHEN C , CHEN J , SHI C . Research on credit evaluation model of online store based on snow NLP[C]// In E3S Web of Conferences,EDP Sciences. 2018(3): 3-39.
[38]	HUANG C L , CHUNG C K , HUI N ,et al. The development of the Chinese linguistic inquiry and word count dictionary[J]. Chinese Journal of Psychology, 2012,54(2): 185-201.
[39]	GAO R , HAO B , LI H ,et al. Brain and health informatics:developing simplified Chinese psychological linguistic analysis dictionary for microblog[M]. Berlin: SpringerPress, 2013: 359-368.
[40]	SCHLEIMER S , WILKERSON D S , AIKEN A . Winnowing:local algorithms for document fingerprinting[C]// The ACM SIGMOD International Conference on Management of Data. ACM, 2003: 76-85.

Metrics

Recommended 0

No Suggested Reading articles found!

T	ID	文本评论内容
0.3	1	“衣服收到了，质量很好，穿上很舒服，也很好看。很喜欢，喜欢的小仙女可以下单哦。”
	2	“很厚实。穿上也很舒服，很喜欢，很喜欢，下次还会来的哦。”
0.5	3	“裤子很好看，穿在身上很暖和，客服推荐的尺码也很准，非常满意。”
	4	“质量很好，面料也舒服。穿上很舒服，颜色也很正，大小也合适，很喜欢。”
0.8	5	“物流快，几天就到手了，因为喜欢宽松的，穿上刚刚好。是我想要的款式，颜色也很正，好评。”
	6	“裤子真的太好看了，少女心满满了。大小合适，特漂亮，已推荐朋友们购买哦。”
1.0	7	“宝贝收到了炒鸡舒服，袖子是松紧的又给朋友买个小一号，没有色差价钱也不贵。好惊喜店家非常认真，物流贼快，下次再来。”
	8	“衣服收到，做工精细，没有色差。款式很美，小妹妹看正合适，价格也不高，穿起来显瘦，总之挺喜欢的，以后还会再来哒。”
1.3	9	“裤子版型款式很潮，胖妹子拍照，换洗小脚裤都很好看。款式新颖大方跟图片描述一模一样。耶哈哈太值了。”
	10	“太稀饭了上身效果好，很厚重，颜色也美观。冬天穿美感，颜色还显皮肤白。领裤都很好看，朋友再入下这种一个小店，合适，袖子太满意啦。”

模型	结构	参数数量/MB	误差					训练时长/h
模型	结构	参数数量/MB	迭代0次	迭代10次	迭代50次	迭代100次	迭代400次	训练时长/h
Char-LSTM	3层LSTM	54	100%	83.14%	63.57%	40.39%	39.42%	24
汉字嵌入LSTM	3层LSTM	4.3	100%	60.13%	42.72%	31.2%	28.93%	5

T	召回率	有效率
0.3	97%	0
0.5	66%	24%
0.8	52%	37%
1.0	43%	48%
1.3	63%	31%

Automated crowdturfing attack in Chinese user reviews

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 40

Related Articles 8

Metrics

Recommended 0

[1]	Hongyan WANG, Hai YUAN. Action recognition method based on fusion of skeleton and apparent features [J]. Journal on Communications, 2022, 43(1): 138-148.
[2]	Wengang MA, Yadong ZHANG, Jin GUO. Abnormal traffic detection method based on LSTM and improved residual neural network optimization [J]. Journal on Communications, 2021, 42(5): 23-40.
[3]	Yuntian FENG, Xia WU, Xiong XU, Rongqing ZHANG. Research on ionospheric parameters prediction based on deep learning [J]. Journal on Communications, 2021, 42(4): 202-206.
[4]	Ruizhang HUANG, Wenfan JIN, Yanping CHEN, Yongbin QIN, Qinghua ZHENG. Research on Chinese predicate head recognition based on Highway-BiLSTM network [J]. Journal on Communications, 2021, 42(1): 100-107.
[5]	Han ZHANG,Yongjin HU,Yuanbo GUO,Jicheng CHEN. Research on coreference resolution technology of entity in information security [J]. Journal on Communications, 2020, 41(2): 165-175.
[6]	Run WANG,Benxiao TANG,Li’na WANG. DeepRD:LSTM-based Siamese network for Android repackaged applications detection [J]. Journal on Communications, 2018, 39(8): 69-82.
[7]	Shui-fei ZENG,Xiao-yan ZHANG,Xiao-feng DU,Tian-bo LU. New method of text representation model based on neural network [J]. Journal on Communications, 2017, 38(4): 86-98.
[8]	You-jun LI,Jia-jin HUANG,Hai-yuan WANG,Ning ZHONG. Study of emotion recognition based on fusion multi-modal bio-signal with SAE and LSTM recurrent neural network [J]. Journal on Communications, 2017, 38(12): 109-120.