research-article

Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction

Authors:

Huajun ChenAuthors Info & Claims

IJCKG '21: Proceedings of the 10th International Joint Conference on Knowledge Graphs

Pages 115 - 120

https://doi.org/10.1145/3502223.3502237

Published: 24 January 2022 Publication History

Abstract

Recent neural-based relation extraction approaches, though achieving promising improvement on benchmark datasets, have reported their vulnerability towards adversarial attacks. Thus far, efforts mostly focused on generating adversarial samples or defending adversarial attacks, but little is known about the difference between normal and adversarial samples. In this work, we take the first step to leverage the salience-based method to analyze those adversarial samples. We observe that salience tokens have a direct correlation with adversarial perturbations. We further find the adversarial perturbations are either those tokens not existing in the training set or superficial cues associated with relation labels. To some extent, our approach unveils the characters against adversarial samples. We release an open-source testbed, “DiagnoseAdv”1, for future research purposes.

References

[1]

Livio Baldini Soares, Nicholas FitzGerald, Jeffrey Ling, and Tom Kwiatkowski. 2019. Matching the Blanks: Distributional Similarity for Relation Learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 2895–2905. https://doi.org/10.18653/v1/P19-1279

[2]

Jasmijn Bastings and Katja Filippova. 2020. The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, Online, 149–155. https://doi.org/10.18653/v1/2020.blackboxnlp-1.14

[3]

Yonatan Belinkov and James R. Glass. 2019. Analysis Methods in Neural Language Processing: A Survey. Trans. Assoc. Comput. Linguistics 7 (2019), 49–72. https://transacl.org/ojs/index.php/tacl/article/view/1570

[4]

Shumin Deng, Ningyu Zhang, Hui Chen, Chuanqi Tan, Fei Huang, Changliang Xu, and Huajun Chen. 2022. Low-resource extraction with knowledge-aware pairwise prototype learning. Knowledge-Based Systems 235 (2022), 107584. https://doi.org/10.1016/j.knosys.2021.107584

Digital Library

[5]

Shumin Deng, Ningyu Zhang, Jiaojian Kang, Yichi Zhang, Wei Zhang, and Huajun Chen. 2020. Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection. In WSDM ’20: The Thirteenth ACM International Conference on Web Search and Data Mining, Houston, TX, USA, February 3-7, 2020, James Caverlee, Xia (Ben) Hu, Mounia Lalmas, and Wei Wang (Eds.). ACM, 151–159. https://doi.org/10.1145/3336191.3371796

Digital Library

[6]

Shumin Deng, Ningyu Zhang, Luoqiu Li, Chen Hui, Huaixiao Tou, Mosha Chen, Fei Huang, and Huajun Chen. 2021. OntoED: Low-resource Event Detection with Ontology Embedding. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (Eds.). Association for Computational Linguistics, 2828–2839. https://doi.org/10.18653/v1/2021.acl-long.220

[7]

Shumin Deng, Ningyu Zhang, Wen Zhang, Jiaoyan Chen, Jeff Z. Pan, and Huajun Chen. 2019. Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolutional Network. In Companion of The 2019 World Wide Web Conference, WWW 2019, San Francisco, CA, USA, May 13-17, 2019, Sihem Amer-Yahia, Mohammad Mahdian, Ashish Goel, Geert-Jan Houben, Kristina Lerman, Julian J. McAuley, Ricardo Baeza-Yates, and Leila Zia (Eds.). ACM, 678–685. https://doi.org/10.1145/3308560.3317701

Digital Library

[8]

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171–4186. https://doi.org/10.18653/v1/N19-1423

[9]

Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou. 2018. HotFlip: White-Box Adversarial Examples for Text Classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 2: Short Papers, Iryna Gurevych and Yusuke Miyao (Eds.). Association for Computational Linguistics, 31–36. https://doi.org/10.18653/v1/P18-2006

[10]

Negin Entezari, Saba A. Al-Sayouri, Amirali Darvishzadeh, and Evangelos E. Papalexakis. 2020. All You Need Is Low (Rank): Defending Against Adversarial Attacks on Graphs. In WSDM ’20: The Thirteenth ACM International Conference on Web Search and Data Mining, Houston, TX, USA, February 3-7, 2020, James Caverlee, Xia (Ben) Hu, Mounia Lalmas, and Wei Wang (Eds.). ACM, 169–177. https://doi.org/10.1145/3336191.3371789

Digital Library

[11]

Ji Gao, Jack Lanchantin, Mary Lou Soffa, and Yanjun Qi. 2018. Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers. In 2018 IEEE Security and Privacy Workshops, SP Workshops 2018, San Francisco, CA, USA, May 24, 2018. IEEE Computer Society, 50–56. https://doi.org/10.1109/SPW.2018.00016

[12]

Xiaochuang Han, Byron C. Wallace, and Yulia Tsvetkov. 2020. Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 5553–5563. https://doi.org/10.18653/v1/2020.acl-main.492

[13]

Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2018. FewRel: A Large-Scale Supervised Few-shot Relation Classification Dataset with State-of-the-Art Evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018, Ellen Riloff, David Chiang, Julia Hockenmaier, and Jun’ichi Tsujii (Eds.). Association for Computational Linguistics, 4803–4809. https://doi.org/10.18653/v1/d18-1514

[14]

Qianghuai Jia, Ningyu Zhang, and Nengwei Hua. 2020. Context-Aware Deep Model for Entity Recommendation System in Search Engine at Alibaba. J. Multim. Process. Technol. 11, 1 (2020), 23–35. https://doi.org/10.6025/jmpt/2020/11/1/23-35

[15]

Di Jin, Zhijing Jin, Joey Tianyi Zhou, and Peter Szolovits. 2020. Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020. AAAI Press, 8018–8025. https://aaai.org/ojs/index.php/AAAI/article/view/6311

[16]

Qiao Jin, Chuanqi Tan, Mosha Chen, Ming Yan, Songfang Huang, Ningyu Zhang, and Xiaozhong Liu. 2020. Aliababa DAMO Academy at TREC Precision Medicine 2020: State-of-the-art Evidence Retriever for Precision Medicine with Expert-in-the-loop Active Learning. In Proceedings of the Twenty-Ninth Text REtrieval Conference, TREC 2020, Virtual Event [Gaithersburg, Maryland, USA], November 16-20, 2020(NIST Special Publication), Ellen M. Voorhees and Angela Ellis (Eds.). Vol. 1266. National Institute of Standards and Technology (NIST). https://trec.nist.gov/pubs/trec29/papers/ALIBABA.PM.pdf

[17]

Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving Pre-training by Representing and Predicting Spans. Trans. Assoc. Comput. Linguistics 8 (2020), 64–77. https://transacl.org/ojs/index.php/tacl/article/view/1853

[18]

Tassilo Klein and Moin Nabi. 2019. Attention Is (not) All You Need for Commonsense Reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, 4831–4836. https://doi.org/10.18653/v1/P19-1477

[19]

Jinfeng Li, Shouling Ji, Tianyu Du, Bo Li, and Ting Wang. 2019. TextBugger: Generating Adversarial Text Against Real-world Applications. In 26th Annual Network and Distributed System Security Symposium, NDSS 2019, San Diego, California, USA, February 24-27, 2019. The Internet Society. https://www.ndss-symposium.org/ndss-paper/textbugger-generating-adversarial-text-against-real-world-applications/

[20]

Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, and Huajun Chen. 2020. Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, Donia Scott, Núria Bel, and Chengqing Zong (Eds.). International Committee on Computational Linguistics, 2967–2978. https://doi.org/10.18653/v1/2020.coling-main.265

[21]

Bin Liang, Hongcheng Li, Miaoqiang Su, Pan Bian, Xirong Li, and Wenchang Shi. 2018. Deep Text Classification Can be Fooled. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden, Jérôme Lang (Ed.). ijcai.org, 4208–4215. https://doi.org/10.24963/ijcai.2018/585

[22]

Dongfang Lou, Zhilin Liao, Shumin Deng, Ningyu Zhang, and Huajun Chen. 2021. MLBiNet: A Cross-Sentence Collective Event Detection Network. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (Eds.). Association for Computational Linguistics, 4829–4839. https://doi.org/10.18653/v1/2021.acl-long.373

[23]

Shuhuai Ren, Yihe Deng, Kun He, and Wanxiang Che. 2019. Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, Anna Korhonen, David R. Traum, and Lluís Màrquez (Eds.). Association for Computational Linguistics, 1085–1097. https://doi.org/10.18653/v1/p19-1103

[24]

Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017(Proceedings of Machine Learning Research), Doina Precup and Yee Whye Teh (Eds.). Vol. 70. PMLR, 3319–3328. http://proceedings.mlr.press/v70/sundararajan17a.html

[25]

Rajkumar Theagarajan, Ming Chen, Bir Bhanu, and Jing Zhang. 2019. ShieldNets: Defending Against Adversarial Attacks Using Probabilistic Adversarial Robustness. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. Computer Vision Foundation / IEEE, 6988–6996. https://doi.org/10.1109/CVPR.2019.00715

[26]

Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh. 2019. Universal Adversarial Triggers for Attacking and Analyzing NLP. 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). Association for Computational Linguistics, Hong Kong, China, 2153–2162. https://doi.org/10.18653/v1/D19-1221

[27]

Zifeng Wang, Rui Wen, Xi Chen, Shao-Lun Huang, Ningyu Zhang, and Yefeng Zheng. 2020. Finding Influential Instances for Distantly Supervised Relation Extraction. CoRR abs/2009.09841(2020). arxiv:2009.09841https://arxiv.org/abs/2009.09841

[28]

Sarah Wiegreffe and Yuval Pinter. 2019. Attention is not not Explanation. 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, Hong Kong, China, November 3-7, 2019, Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan (Eds.). Association for Computational Linguistics, 11–20. https://doi.org/10.18653/v1/D19-1002

[29]

Zhilin Yang, Zihang Dai, Yiming Yang, Jaime G. Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett (Eds.). 5754–5764. https://proceedings.neurips.cc/paper/2019/hash/dc6a7e655d7e5840e66733e9ee67cc69-Abstract.html

[30]

Hongbin Ye, Ningyu Zhang, Zhen Bi, Shumin Deng, Chuanqi Tan, Hui Chen, Fei Huang, and Huajun Chen. 2021. Learning to Ask for Data-Efficient Event Argument Extraction. CoRR abs/2110.00479(2021). arXiv:2110.00479https://arxiv.org/abs/2110.00479

[31]

Hongbin Ye, Ningyu Zhang, Shumin Deng, Mosha Chen, Chuanqi Tan, Fei Huang, and Huajun Chen. 2020. Contrastive Triple Extraction with Generative Transformer. CoRR abs/2009.06207(2020). arxiv:2009.06207https://arxiv.org/abs/2009.06207

[32]

Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei Zhang, and Huajun Chen. 2020. Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, Donia Scott, Núria Bel, and Chengqing Zong (Eds.). International Committee on Computational Linguistics, 6399–6410. https://doi.org/10.18653/v1/2020.coling-main.563

[33]

Haiyang Yu, Ningyu Zhang, Shumin Deng, Zonggang Yuan, Yantao Jia, and Huajun Chen. 2020. The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis. CoRR abs/2009.07022(2020). arxiv:2009.07022https://arxiv.org/abs/2009.07022

[34]

Yuan Zang, Fanchao Qi, Chenghao Yang, Zhiyuan Liu, Meng Zhang, Qun Liu, and Maosong Sun. 2020. Word-level Textual Adversarial Attacking as Combinatorial Optimization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 6066–6080. https://doi.org/10.18653/v1/2020.acl-main.540

[35]

Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, and Jun Zhao. 2014. Relation Classification via Convolutional Deep Neural Network. In COLING 2014, 25th International Conference on Computational Linguistics, Proceedings of the Conference: Technical Papers, August 23-29, 2014, Dublin, Ireland, Jan Hajic and Junichi Tsujii (Eds.). ACL, 2335–2344. https://www.aclweb.org/anthology/C14-1220/

[36]

Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Luo Si, and Huajun Chen. 2021. Document-level Relation Extraction as Semantic Segmentation. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, Zhi-Hua Zhou (Ed.). ijcai.org, 3999–4006. https://doi.org/10.24963/ijcai.2021/551

[37]

Ningyu Zhang, Shumin Deng, Zhen Bi, Haiyang Yu, Jiacheng Yang, Mosha Chen, Fei Huang, Wei Zhang, and Huajun Chen. 2020. OpenUE: An Open Toolkit of Universal Extraction from Text. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2020 - Demos, Online, November 16-20, 2020, Qun Liu and David Schlangen (Eds.). Association for Computational Linguistics, 1–8. https://doi.org/10.18653/v1/2020.emnlp-demos.1

[38]

Ningyu Zhang, Shumin Deng, Juan Li, Xi Chen, Wei Zhang, and Huajun Chen. 2020. Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, EMNLP 2020, Online Event, 16-20 November 2020, Trevor Cohn, Yulan He, and Yang Liu (Eds.). Association for Computational Linguistics, 15–24. https://doi.org/10.18653/v1/2020.findings-emnlp.2

[39]

Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoyan Chen, Wei Zhang, and Huajun Chen. 2020. Relation Adversarial Network for Low Resource Knowledge Graph Completion. In WWW ’20: The Web Conference 2020, Taipei, Taiwan, April 20-24, 2020, Yennun Huang, Irwin King, Tie-Yan Liu, and Maarten van Steen (Eds.). ACM / IW3C2, 1–12. https://doi.org/10.1145/3366423.3380089

Digital Library

[40]

Ningyu Zhang, Shumin Deng, Zhanling Sun, Xi Chen, Wei Zhang, and Huajun Chen. 2018. Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 986–992. https://doi.org/10.18653/v1/D18-1120

[41]

Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang, and Huajun Chen. 2019. Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 3016–3025. https://doi.org/10.18653/v1/n19-1306

[42]

Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei Zhang, and Huajun Chen. 2022. Robust triple extraction with cascade bidirectional capsule network. Expert Syst. Appl. 187(2022), 115806. https://doi.org/10.1016/j.eswa.2021.115806

[43]

Ningyu Zhang, Qianghuai Jia, Kangping Yin, Liang Dong, Feng Gao, and Nengwei Hua. 2020. Conceptualized Representation Learning for Chinese Biomedical Text Mining. CoRR abs/2008.10813(2020). arxiv:2008.10813https://arxiv.org/abs/2008.10813

[44]

Ningyu Zhang, Luoqiu Li, Shumin Deng, Haiyang Yu, Xu Cheng, Wei Zhang, and Huajun Chen. 2020. Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction. CoRR abs/2009.06206(2020). arxiv:2009.06206https://arxiv.org/abs/2009.06206

[45]

Ningyu Zhang, Hongbin Ye, Shumin Deng, Chuanqi Tan, Mosha Chen, Songfang Huang, Fei Huang, and Huajun Chen. 2021. Contrastive Information Extraction With Generative Transformer. IEEE ACM Trans. Audio Speech Lang. Process. 29 (2021), 3077–3088. https://doi.org/10.1109/TASLP.2021.3110126

Digital Library

[46]

Wei Emma Zhang, Quan Z. Sheng, Ahoud Abdulrahmn F. Alhazmi, and Chenliang Li. 2020. Adversarial Attacks on Deep-learning Models in Natural Language Processing: A Survey. ACM Trans. Intell. Syst. Technol. 11, 3 (2020), 24:1–24:41. https://doi.org/10.1145/3374217

Digital Library

[47]

Yuhao Zhang, Victor Zhong, Danqi Chen, Gabor Angeli, and Christopher D. Manning. 2017. Position-aware Attention and Supervised Data Improve Slot Filling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, Martha Palmer, Rebecca Hwa, and Sebastian Riedel (Eds.). Association for Computational Linguistics, 35–45. https://doi.org/10.18653/v1/d17-1004

[48]

Hengyi Zheng, Rui Wen, Xi Chen, Yifan Yang, Yunyan Zhang, Ziheng Zhang, Ningyu Zhang, Bin Qin, Xu Ming, and Yefeng Zheng. 2021. PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (Eds.). Association for Computational Linguistics, 6225–6235. https://doi.org/10.18653/v1/2021.acl-long.486

Cited By

Liu YFu LXia XZhang Y(2024)Exploring the Role of Self-Adaptive Feature Words in Relation Quintuple Extraction for Scientific LiteratureApplied Sciences10.3390/app1410402014:10(4020)Online publication date: 9-May-2024
https://doi.org/10.3390/app14104020
Li LChen XYe HBi ZDeng SZhang NChen H(2021)On Robustness and Bias Analysis of BERT-Based Relation ExtractionKnowledge Graph and Semantic Computing: Knowledge Graph Empowers New Infrastructure Construction10.1007/978-981-16-6471-7_4(43-59)Online publication date: 28-Oct-2021
https://doi.org/10.1007/978-981-16-6471-7_4

Index Terms

Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
  2. Machine learning
    1. Learning paradigms
    2. Machine learning approaches

Index terms have been assigned to the content through auto-classification.

Recommendations

Detection by Attack: Detecting Adversarial Samples by Undercover Attack
Computer Security – ESORICS 2020
Abstract
The safety of artificial intelligence systems has aroused great concern due to the vulnerability of deep neural networks. Studies show that malicious modifications to the inputs of a network classifier, can fool the classifier and lead to wrong ...
A defense method based on attention mechanism against traffic sign adversarial samples
Abstract
A traditional neural network cannot realize the invariance of image rotation and distortion well, so an attacker can fool the neural network by adding tiny disturbances to an image. If traffic signs are attacked, automatic driving will probably ...
Highlights
- The attacker can cheat the neural network by adding tiny disturbance to the image.
- If traffic signs are attacked, automatic driving will probably be misguided.
- The key areas in the image are extracted by the attention mechanism.
Learning relationship-preserving representation for multi-task adversarial attacks
Abstract
Deep neural networks (DNNs) are susceptible to adversarial samples that are carefully crafted to mislead the DNNs with imperceptible perturbations. To test the robustness of DNNs, attack methods based on adversarial samples have gained ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

IJCKG '21: Proceedings of the 10th International Joint Conference on Knowledge Graphs

December 2021

204 pages

ISBN:9781450395656

DOI:10.1145/3502223

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 January 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

NSFC

Conference

IJCKG'21

IJCKG'21: The 10th International Joint Conference on Knowledge Graphs

December 6 - 8, 2021

Virtual Event, Thailand

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
93
Total Downloads

Downloads (Last 12 months)12
Downloads (Last 6 weeks)1

Reflects downloads up to 30 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Liu YFu LXia XZhang Y(2024)Exploring the Role of Self-Adaptive Feature Words in Relation Quintuple Extraction for Scientific LiteratureApplied Sciences10.3390/app1410402014:10(4020)Online publication date: 9-May-2024
https://doi.org/10.3390/app14104020
Li LChen XYe HBi ZDeng SZhang NChen H(2021)On Robustness and Bias Analysis of BERT-Based Relation ExtractionKnowledge Graph and Semantic Computing: Knowledge Graph Empowers New Infrastructure Construction10.1007/978-981-16-6471-7_4(43-59)Online publication date: 28-Oct-2021
https://doi.org/10.1007/978-981-16-6471-7_4

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents