AI Total: Analyzing Security ML Models with Imperfect Data in Production

被引:2
作者
Sopan, Awalin [1 ]
Berlin, Konstantin [1 ]
机构
[1] Sophos, Abingdon, Oxon, England
来源
2021 IEEE SYMPOSIUM ON VISUALIZATION FOR CYBER SECURITY (VIZSEC 2021) | 2021年
关键词
D O I
10.1109/VizSec53666.2021.00006
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Development of new machine learning models is typically done on manually curated data sets, making them unsuitable for evaluating the models' performance during operations, where the evaluation needs to be performed automatically on incoming streams of new data. Unfortunately, pure reliance on a fully automatic pipeline for monitoring model performance makes it difficult to understand if any observed performance issues are due to model performance, pipeline issues, emerging data distribution biases, or some combination of the above. With this in mind, we developed a web-based visualization system that allows the users to quickly gather headline performance numbers while maintaining confidence that the underlying data pipeline is functioning properly. It also enables the users to immediately observe the root cause of an issue when something goes wrong. We introduce a novel way to analyze performance under data issues using a data coverage equalizer. We describe the various modifications and additional plots, filters, and drill-downs that we added on top of the standard evaluation metrics typically tracked in machine learning (ML) applications, and walk through some real world examples that proved valuable for introspecting our models.
引用
收藏
页码:10 / 14
页数:5
相关论文
共 22 条
  • [1] Software Engineering for Machine Learning: A Case Study
    Amershi, Saleema
    Begel, Andrew
    Bird, Christian
    DeLine, Robert
    Gall, Harald
    Kamar, Ece
    Nagappan, Nachiappan
    Nushi, Besmira
    Zimmermann, Thomas
    [J]. 2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: SOFTWARE ENGINEERING IN PRACTICE (ICSE-SEIP 2019), 2019, : 291 - 300
  • [2] ModelTracker: Redesigning Performance Analysis Tools for Machine Learning
    Amershi, Saleema
    Chickering, Max
    Drucker, Steven M.
    Lee, Bongshin
    Simard, Patrice
    Suh, Jina
    [J]. CHI 2015: PROCEEDINGS OF THE 33RD ANNUAL CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, 2015, : 337 - 346
  • [3] DeepDGA: Adversarially-Tuned Domain Generation and Detection
    Anderson, Hyrum S.
    Woodbridge, Jonathan
    Filar, Bobby
    [J]. AISEC'16: PROCEEDINGS OF THE 2016 ACM WORKSHOP ON ARTIFICIAL INTELLIGENCE AND SECURITY, 2016, : 13 - 21
  • [4] [Anonymous], 2017, P 14 IEEE S VIS CYB, DOI DOI 10.1109/VIZSEC.2017.8062199
  • [5] Aporia, 2017, EAS MON MACH LEARN M
  • [6] Blowers M., 2014, NETWORK SCI CYBERSEC, P155
  • [7] Bosch J., 2021, Artificial Intelligence Paradigms for Smart Cyber-Physical Systems, P1
  • [8] Breck E., 2019, MLSYS
  • [9] Breck E, 2017, IEEE INT CONF BIG DA, P1123, DOI 10.1109/BigData.2017.8258038
  • [10] Chatzimparmpas A., 2021, ARXIV PREPRINT ARXIV