2023

Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process

Ni, Mingze, Sun, Zhensu, Liu, Wei

Understand

Recent research has revealed that natural language processing (NLP) models are vulnerable to adversarial examples.

However, the current techniques for generating such examples rely on deterministic heuristic rules, which fail to produce optimal adversarial examples.
In response, this study proposes a new method called the Fraud's Bargain Attack (FBA), which uses a randomization mechanism to expand the search space and produce high-quality adversarial examples with a higher probability of success.
FBA uses the Metropolis-Hasting sampler, a type of Markov Chain Monte Carlo sampler, to improve the selection of adversarial examples from all candidates generated by a customized stochastic process called the Word Manipulation Process (WMP).

Built on

N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller, and E. Teller, “Equation of state calculations by fast computing machines,” The journal of chemical physics , vol. 21, no. 6, pp. 1087–1092, 1953
1953
Earlier work this paper cites.
W. K. Hastings, “Monte carlo sampling methods using markov chains and their applications,” Biometrika , vol. 57, pp. 97–109, 1970. [Online]. Available: https://api.semanticscholar.org/CorpusID:21204149
1970
Earlier work this paper cites.
G. A. Miller, R. Beckwith, C. Fellbaum, D. Gross, and K. J. Miller, “Introduction to wordnet: An on-line lexical database,” International journal of lexicography , vol. 3, no. 4, pp. 235–244, 1990
1990
Earlier work this paper cites.
R. Rubinstein, “The cross-entropy method for combinatorial and continuous optimization,” Methodology and computing in applied probability , vol. 1, no. 2, pp. 127–190, 1999
1999
Earlier work this paper cites.
Z. Dong and Q. Dong, “Hownet-a hybrid language and knowledge resource,” in International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003 . IEEE, 2003, pp. 820–824
2003
Earlier work this paper cites.
D. Naber et al. , “A rule-based style and grammar checker,” Citeseer , 2003
2003
Earlier work this paper cites.
X. Kang and F. Ren, “Sampling latent emotions and topics in a hierarchical bayesian network,” 2011 7th International Conference on Natural Language Processing and Knowledge Engineering , pp. 37–42, 2011
2011
Earlier work this paper cites.
D. P. Kroese, T. Taimre, and Z. I. Botev, Handbook of Monte Carlo Methods . John Wiley & Sons, 2011
2011
Earlier work this paper cites.
S. Singh, M. L. Wick, and A. McCallum, “Monte carlo mcmc: Efficient inference by sampling factors,” in AKBC-WEKEX@NAACL-HLT , 2012
2012
Earlier work this paper cites.
T. Mikolov, K. Chen, G. S. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” in ICLR , 2013
2013
Earlier work this paper cites.
R. Socher, A. Perelygin, J. Wu, J. Chuang, C. D. Manning, A. Ng, and C. Potts, “Recursive deep models for semantic compositionality over a sentiment treebank,” in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing . Seattle, Washington, USA: Association for Computational Linguistics, Oct. 2013, pp. 1631–1642
2013
Earlier work this paper cites.
J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation,” in Empirical Methods in Natural Language Processing (EMNLP) , 2014, pp. 1532–1543
2014
Earlier work this paper cites.
I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” CoRR , vol. abs/1412.6572, 2015
Original
2015
Earlier work this paper cites.
G. A. Pavliotis, “Stochastic processes and applications,” Informe técnico , 2015
2015
Earlier work this paper cites.
X. Zhang, J. J. Zhao, and Y. LeCun, “Character-level convolutional networks for text classification,” in NIPS , 2015
2015
Earlier work this paper cites.
N. Papernot, P. D. McDaniel, A. Swami, and R. E. Harang, “Crafting adversarial input sequences for recurrent neural networks,” CoRR , vol. abs/1604.08275, 2016
Original
2016
Earlier work this paper cites.
N. Mrkšić, D. Ó. Séaghdha, B. Thomson, M. Gasic, L. M. R. Barahona, P.-H. Su, D. Vandyke, T.-H. Wen, and S. Young, “Counter-fitting word vectors to linguistic constraints,” in Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , 2016, pp. 142–148
2016
Earlier work this paper cites.

Similar

K. Kumagai, I. Kobayashi, D. Mochihashi, H. Asoh, T. Nakamura, and T. Nagai, “Human-like natural language generation using monte carlo tree search,” in CC-NLG , 2016
2016
Cited alongside, same era.
J. Ebrahimi, A. Rao, D. Lowd, and D. Dou, “Hotflip: White-box adversarial examples for text classification,” arXiv preprint arXiv:1712.06751 , 2017
Original
2017
Cited alongside, same era.
B. Harrison, C. Purdy, and M. O. Riedl, “Toward automated story generation with markov chain monte carlo methods and deep neural networks,” in Thirteenth Artificial Intelligence and Interactive Digital Entertainment Conference , 2017
2017
Cited alongside, same era.
M. Alzantot, Y. Sharma, A. Elgohary, B.-J. Ho, M. Srivastava, and K.-W. Chang, “Generating natural language adversarial examples,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , 2018, pp. 2890–2896
2018
Cited alongside, same era.
X. Fan, B. Li, and S. Sisson, “Rectangular bounding process,” Advances in Neural Information Processing Systems , vol. 31, 2018
2018
Cited alongside, same era.
D. Cer, Y. Yang, S.-y. Kong, N. Hua, N. Limtiaco, R. S. John, N. Constant, M. Guajardo-Cespedes, S. Yuan, C. Tar et al. , “Universal sentence encoder for english,” in Proceedings of the 2018 conference on empirical methods in natural language processing: system demonstrations , 2018, pp. 169–174
2018
Cited alongside, same era.
E. Saravia, H.-C. T. Liu, Y.-H. Huang, J. Wu, and Y.-S. Chen, “CARER: Contextualized affect representations for emotion recognition,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing . Brussels, Belgium: Association for Computational Linguistics, Oct.-Nov. 2018, pp. 3687–3697
2018
Cited alongside, same era.
W. C. Gan and H. T. Ng, “Improving the robustness of question answering systems to question paraphrasing,” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics , 2019, pp. 6065–6075
2019
Cited alongside, same era.
S. Ren, Y. Deng, K. He, and W. Che, “Generating natural language adversarial examples through probability weighted word saliency,” in Proceedings of the 57th annual meeting of the association for computational linguistics , 2019, pp. 1085–1097
2019
Cited alongside, same era.
R. Jia, A. Raghunathan, K. Göksel, and P. Liang, “Certified robustness to adversarial word substitutions,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) , 2019, pp. 4129–4142
2019
Cited alongside, same era.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” in NAACL , 2019
2019
Cited alongside, same era.
Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, “Roberta: A robustly optimized bert pretraining approach,” ArXiv , vol. abs/1907.11692, 2019
Original
2019
Cited alongside, same era.

Then

Y. Zang, F. Qi, C. Yang, Z. Liu, M. Zhang, Q. Liu, and M. Sun, “Word-level textual adversarial attacking as combinatorial optimization,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , 2020, pp. 6066–6080
2020
Later among the works it cites.
L. Li, R. Ma, Q. Guo, X. Xue, and X. Qiu, “Bert-attack: Adversarial attack against bert using bert,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 2020, pp. 6193–6202
2020
Later among the works it cites.
A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán, E. Grave, M. Ott, L. Zettlemoyer, and V. Stoyanov, “Unsupervised cross-lingual representation learning at scale,” in ACL , 2020
2020
Later among the works it cites.
K. Song, X. Tan, T. Qin, J. Lu, and T.-Y. Liu, “Mpnet: Masked and permuted pre-training for language understanding,” Advances in Neural Information Processing Systems , vol. 33, pp. 16 857–16 867, 2020
2020
Later among the works it cites.
D. Jin, Z. Jin, J. T. Zhou, and P. Szolovits, “Is bert really robust? a strong baseline for natural language attack on text classification and entailment,” in AAAI , 2020
2020
Later among the works it cites.
A. S. Chivukula, X. Yang, W. Liu, T. Zhu, and W. Zhou, “Game theoretical adversarial deep learning with variational adversaries,” IEEE Transactions on Knowledge and Data Engineering (TKDE) , vol. 33, no. 11, pp. 3568–3581, 2020
2020
Later among the works it cites.
X. Yang, W. Liu, J. Bailey, D. Tao, and W. Liu, “Bigram and unigram based text attack via adaptive monotonic heuristic search,” in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 35, no. 1, 2021, pp. 706–714
2021
Later among the works it cites.
H. Sun, T. Zhu, Z. Zhang, D. Jin, P. Xiong, and W. Zhou, “Adversarial attacks against deep generative models on data: A survey,” IEEE Transactions on Knowledge Data Engineering (TKDE) , pp. 1–1, nov 2021
2021
Later among the works it cites.
J. F. Haase, L. Dellantonio, A. Celi, D. Paulson, A. Kan, K. Jansen, and C. A. Muschik, “A resource efficient approach for quantum and classical simulations of gauge theories in particle physics,” Quantum , vol. 5, p. 393, 2021
2021
Later among the works it cites.
D. Li, Y. Zhang, H. Peng, L. Chen, C. Brockett, M.-T. Sun, and W. B. Dolan, “Contextualized perturbation for textual adversarial attack,” in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , 2021, pp. 5053–5069
2021
Later among the works it cites.
J. Y. Yoo and Y. Qi, “Towards improving adversarial training of nlp models,” in Findings of the Association for Computational Linguistics: EMNLP 2021 , 2021, pp. 945–956
2021
Later among the works it cites.
M. Ni, C. Wang, T. Zhu, S. Yu, and W. Liu, “Attacking neural machine translations via hybrid attention learning,” Machine Learning , pp. 1–26, 2022
2022
Later among the works it cites.
H. Xia, S. Shao, C. Hu, R. Zhang, T. Qiu, and F. Xiao, “Robust clustering model based on attention mechanism and graph convolutional network,” IEEE Transactions on Knowledge and Data Engineering (TKDE) , pp. 1–1, 2022
2022
Later among the works it cites.
X. Ding, H. Fang, Z. Zhang, K.-K. R. Choo, and H. Jin, “Privacy-preserving feature extraction via adversarial training,” IEEE Transactions on Knowledge and Data Engineering (TKDE) , vol. 34, no. 4, pp. 1967–1979, 2022
2022
Later among the works it cites.
W. Wang, R. Wang, L. Wang, Z. Wang, and A. Ye, “Towards a robust deep neural network against adversarial texts: A survey,” IEEE Transactions on Knowledge and Data Engineering(TKDE) , vol. 35, no. 3, pp. 3159–3179, 2023
2023
Closest in time.
M. Ni, Z. Sun, and W. Liu, “Fraud’s bargain attacks to textual classifiers via metropolis-hasting sampling (student abstract),” in Proceedings of the AAAI Conference on Artificial Intelligence , 2023
2023
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…