poster

PORDE: Explaining Data Poisoning Attacks Through Visual Analytics with Food Delivery App Reviews

Authors:

Hyunggu JungAuthors Info & Claims

IUI '23 Companion: Companion Proceedings of the 28th International Conference on Intelligent User Interfaces

Pages 46 - 50

https://doi.org/10.1145/3581754.3584128

Published: 27 March 2023 Publication History

Abstract

Artificial intelligence (AI) gives many benefits to our lives. However, biased AI models created by receiving data poisoning attacks may induce social problems. Therefore, developers must consider carefully whether the training data received a poison attack when developing an AI model. Data visualization is one of the methods to facilitate the analysis of the data required for checking if the training data received a poisoning attack. However, prior studies did not visualize real-world AI training data. Restaurant reviews in delivery apps are one of the cases of a poisoned dataset. Restaurants hold review events on delivery apps to encourage customers to write a positive review in return for certain rewards, thereby creating reviews with bias. In this study, we propose POisoned Real-world Data Explainer (PORDE) that explains data poisoning attacks through visual analytics with food delivery app reviews. The findings of this study suggest implications for securing safe training data and developing less biased AI models.

References

[1]

Michael Bostock, Vadim Ogievetsky, and Jeffrey Heer. 2011. D³ Data-Driven Documents. IEEE Transactions on Visualization and Computer Graphics 17, 12(2011), 2301–2309. https://doi.org/10.1109/TVCG.2011.185

Digital Library

[2]

Sam De Craemer, Karen Driesen, and Bart Ghesquière. 2022. TraVis Pies: A Guide for Stable Isotope Metabolomics Interpretation Using an Intuitive Visualization. Metabolites 12, 7 (June 2022), 593. https://doi.org/10.3390/metabo12070593

[3]

Li Deng. 2012. The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]. IEEE Signal Processing Magazine 29, 6 (2012), 141–142. https://doi.org/10.1109/MSP.2012.2211477

[4]

Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http://archive.ics.uci.edu/ml

[5]

Jim Gao. 2014. Machine Learning Applications for Data Center Optimization.

[6]

Bhavya Ghai, Md Naimul Hoque, and Klaus Mueller. 2021. WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings. In Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan) (CHI EA ’21). Association for Computing Machinery, New York, NY, USA, Article 429, 7 pages. https://doi.org/10.1145/3411763.3451587

Digital Library

[7]

Bhavya Ghai and Klaus Mueller. 2023. D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias. IEEE Transactions on Visualization and Computer Graphics 29, 1(2023), 473–482. https://doi.org/10.1109/TVCG.2022.3209484

[8]

David Gotz, Shun Sun, and Nan Cao. 2016. Adaptive Contextualization: Combating Bias During High-Dimensional Visualization and Data Selection. In Proceedings of the 21st International Conference on Intelligent User Interfaces (Sonoma, California, USA) (IUI ’16). Association for Computing Machinery, New York, NY, USA, 85–95. https://doi.org/10.1145/2856767.2856779

Digital Library

[9]

David Gotz, Shun Sun, Nan Cao, Rita Kundu, and Anne-Marie Meyer. 2017. Adaptive Contextualization Methods for Combating Selection Bias during High-Dimensional Visualization. ACM Trans. Interact. Intell. Syst. 7, 4, Article 17 (Nov. 2017), 23 pages. https://doi.org/10.1145/3009973

Digital Library

[10]

Henry Han and Ke Men. 2018. How does normalization impact RNA-seq disease diagnosis?Journal of Biomedical Informatics 85 (2018), 80–92. https://doi.org/10.1016/j.jbi.2018.07.016

Digital Library

[11]

Jinbin Huang, Aditi Mishra, Bum Chul Kwon, and Chris Bryan. 2023. ConceptExplainer: Interactive Explanation for Deep Neural Networks from a Concept Perspective. IEEE Transactions on Visualization and Computer Graphics 29, 1(2023), 831–841. https://doi.org/10.1109/TVCG.2022.3209384

[12]

Renpei Huang, Quan Li, Li Chen, and Xiaoru Yuan. 2022. A Probability Density-Based Visual Analytics Approach to Forecast Bias Calibration. IEEE Transactions on Visualization and Computer Graphics 28, 4(2022), 1732–1744. https://doi.org/10.1109/TVCG.2020.3025072

[13]

Mohaiminul Islam and Shangzhu Jin. 2019. An Overview of Data Visualization. In 2019 International Conference on Information Science and Communications Technologies (ICISCT). IEEE, IEEE, Tashkent, Uzbekistan, 1–7. https://doi.org/10.1109/ICISCT47635.2019.9012031

[14]

Alina Lazar, Ling Jin, C. Anna Spurlock, Kesheng Wu, Alex Sim, and Annika Todd. 2019. Evaluating the Effects of Missing Values and Mixed Data Types on Social Sequence Clustering Using T-SNE Visualization. J. Data and Information Quality 11, 2, Article 7 (Mar. 2019), 22 pages. https://doi.org/10.1145/3301294

Digital Library

[15]

Mohan Li, Yanbin Sun, Hui Lu, Sabita Maharjan, and Zhihong Tian. 2020. Deep Reinforcement Learning for Partially Observable Data Poisoning Attack in Crowdsensing Systems. IEEE Internet of Things Journal 7, 7 (2020), 6266–6278. https://doi.org/10.1109/JIOT.2019.2962914

[16]

Yuxin Ma, Tiankai Xie, Jundong Li, and Ross Maciejewski. 2020. Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics. IEEE Transactions on Visualization and Computer Graphics 26, 1(2020), 1075–1085. https://doi.org/10.1109/TVCG.2019.2934631

[17]

Naiara Muro, Nekane Larburu, Jacques Bouaud, and Brigitte Seroussi. 2019. Gathering Real World Evidence Through the Evaluation of Decision History. Stud Health Technol Inform 262 (July 2019), 134–137. https://doi.org/10.3233/SHTI190035

[18]

Rangeet Pan and Hridesh Rajan. 2022. Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules. In Proceedings of the 44th International Conference on Software Engineering (Pittsburgh, Pennsylvania) (ICSE ’22). Association for Computing Machinery, New York, NY, USA, 524–535. https://doi.org/10.1145/3510003.3510051

Digital Library

[19]

Andrea Paudice, Luis Muñoz-González, and Emil C. Lupu. 2019. Label Sanitization Against Label Flipping Poisoning Attacks. In ECML PKDD 2018 Workshops. Springer International Publishing, Dublin, Ireland, 5–15. https://doi.org/10.1007/978-3-030-13453-2_1

Digital Library

[20]

Andrea Paudice, Luis Muñoz-González, Andras Gyorgy, and Emil C. Lupu. 2018. Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection. https://doi.org/10.48550/ARXIV.1802.03041

[21]

Periklis Perikleous, Andreas Kafkalias, Zenonas Theodosiou, Pinar Barlas, Evgenia Christoforou, Jahna Otterbacher, Gianluca Demartini, and Andreas Lanitis. 2022. How Does the Crowd Impact the Model? A Tool for Raising Awareness of Social Bias in Crowdsourced Training Data. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (Atlanta, GA, USA) (CIKM ’22). Association for Computing Machinery, New York, NY, USA, 4951–4954. https://doi.org/10.1145/3511808.3557178

Digital Library

[22]

Yasamin Salimi, Daniel Domingo-Fernández, Carlos Bobis-Álvarez, Martin Hofmann-Apitius, Colin Birkenbihl, and The Japanese Alzheimer’s Disease Neuroimaging Initiative for the Alzheimer’s Disease Neuroimaging Initiative, for the Aging Brain: Vasculature. 2022. ADataViewer: exploring semantically harmonized Alzheimer’s disease cohort datasets. Alzheimer’s Research & Therapy 14, 1 (May 2022), 69. https://doi.org/10.1186/s13195-022-01009-4

[23]

Guido Van Rossum and Fred L. Drake. 2009. Python 3 Reference Manual. CreateSpace, Scotts Valley, CA.

[24]

Emily Wall, Leslie Blaha, Celeste Paul, and Alex Endert. 2019. A Formative Study of Interactive Bias Metrics in Visual Analytics Using Anchoring Bias. In Human-Computer Interaction – INTERACT 2019, David Lamas, Fernando Loizides, Lennart Nacke, Helen Petrie, Marco Winckler, and Panayiotis Zaphiris (Eds.). Springer International Publishing, Cham, 555–575. https://doi.org/10.1007/978-3-030-29384-0_34

Digital Library

[25]

Samira Yeasmin. 2019. Benefits of Artificial Intelligence in Medicine. In 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS). IEEE, IEEE, Riyadh, Saudi Arabia, 1–6. https://doi.org/10.1109/CAIS.2019.8769557

[26]

Kyra Yee, Uthaipon Tantipongpipat, and Shubhanshu Mishra. 2021. Image Cropping on Twitter: Fairness Metrics, Their Limitations, and the Importance of Representation, Design, and Agency. Proc. ACM Hum.-Comput. Interact. 5, CSCW2, Article 450 (Oct. 2021), 24 pages. https://doi.org/10.1145/3479594

Digital Library

Cited By

Yoo TLee HOh SKwon HJung H(2023)Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow HubCompanion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing10.1145/3584931.3606959(206-211)Online publication date: 14-Oct-2023
https://dl.acm.org/doi/10.1145/3584931.3606959

Index Terms

PORDE: Explaining Data Poisoning Attacks Through Visual Analytics with Food Delivery App Reviews
1. Human-centered computing
  1. Visualization
    1. Visualization systems and tools
2. Information systems
  1. Information systems applications
    1. Decision support systems
      1. Data analytics

Recommendations

Data Poisoning Attacks on Crowdsourcing Learning
Web and Big Data
Abstract
Understanding and assessing the vulnerability of crowdsourcing learning against data poisoning attacks is the key to ensure the quality of classifiers trained from crowdsourced labeled data. Existing studies on data poisoning attacks only focus on ...
A Scalable Mixture Model Based Defense Against Data Poisoning Attacks on Classifiers
Dynamic Data Driven Applications Systems
Abstract
Classifiers, e.g., those based on Naive Bayes, a support vector machine, or even a neural network, are highly susceptible to a data-poisoning attack. The attack objective is to degrade classification accuracy by covertly embedding malicious (...
Evaluation Framework for Poisoning Attacks on Knowledge Graph Embeddings
Natural Language Processing and Chinese Computing
Abstract
In the area of knowledge graph embedding data poisoning, attackers are beginning to consider the importance of poisoning sample exposure risk while increasing the toxicity of the poisoning sample. On the other hand, we have found that some ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

IUI '23 Companion: Companion Proceedings of the 28th International Conference on Intelligent User Interfaces

March 2023

266 pages

ISBN:9798400701078

DOI:10.1145/3581754

Copyright © 2023 Owner/Author.

Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 March 2023

Check for updates

Author Tags

Qualifiers

Poster
Research
Refereed limited

Funding Sources

National Research Foundation of Korea

Conference

IUI '23

Sponsor:

IUI '23: 28th International Conference on Intelligent User Interfaces

March 27 - 31, 2023

NSW, Sydney, Australia

Acceptance Rates

Overall Acceptance Rate 746 of 2,811 submissions, 27%

Upcoming Conference

IUI '25

Sponsor:
sigai
sigai

30th International Conference on Intelligent User Interfaces

March 24 - 27, 2025

Cagliari , Italy

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
209
Total Downloads

Downloads (Last 12 months)83
Downloads (Last 6 weeks)5

Reflects downloads up to 10 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yoo TLee HOh SKwon HJung H(2023)Visualizing the Carbon Intensity of Machine Learning Inference for Image Analysis on TensorFlow HubCompanion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing10.1145/3584931.3606959(206-211)Online publication date: 14-Oct-2023
https://dl.acm.org/doi/10.1145/3584931.3606959

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