Anomalous Example Detection in Deep Learning: A Survey

被引:105
|
作者
Bulusu, Saikiran [1 ]
Kailkhura, Bhavya [2 ]
Li, Bo [3 ]
Varshney, Pramod K. [1 ]
Song, Dawn [4 ]
机构
[1] Syracuse Univ, EECS Dept, Syracuse, NY 13244 USA
[2] Lawrence Livermore Natl Lab, Livermore, CA 94550 USA
[3] Univ Illinois, Comp Sci Dept, Champaign, IL 61820 USA
[4] Univ Calif Berkeley, EECS Dept, Berkeley, CA 94720 USA
关键词
Anomaly detection; Machine learning; Training data; Data models; Training; Neural networks; Licenses; out-of-distribution; adversarial examples; deep learning; neural network; MALWARE DETECTION; AUTOENCODER; NETWORKS;
D O I
10.1109/ACCESS.2020.3010274
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications. We provide a taxonomy for existing techniques based on their underlying assumptions and adopted approaches. We discuss various techniques in each of the categories and provide the relative strengths and weaknesses of the approaches. Our goal in this survey is to provide an easier yet better understanding of the techniques belonging to different categories in which research has been done on this topic. Finally, we highlight the unsolved research challenges while applying anomaly detection techniques in DL systems and present some high-impact future research directions.
引用
收藏
页码:132330 / 132347
页数:18
相关论文
共 50 条
  • [1] Deep Learning for Medical Anomaly Detection - A Survey
    Fernando, Tharindu
    Gammulle, Harshala
    Denman, Simon
    Sridharan, Sridha
    Fookes, Clinton
    ACM COMPUTING SURVEYS, 2021, 54 (07)
  • [2] Modified Autoencoder Training and Scoring for Robust Unsupervised Anomaly Detection in Deep Learning
    Merrill, Nicholas
    Eskandarian, Azim
    IEEE ACCESS, 2020, 8 : 101824 - 101833
  • [3] A Deep Learning Model for Anomalous Wireless Link Detection
    Bertalanic, Blaz
    Yetgin, Halil
    Cerar, Gregor
    Fortuna, Carolina
    2021 17TH INTERNATIONAL CONFERENCE ON WIRELESS AND MOBILE COMPUTING, NETWORKING AND COMMUNICATIONS (WIMOB 2021), 2021, : 265 - 270
  • [4] Towards a Hybrid Deep Learning Model for Anomalous Activities Detection in Internet of Things Networks
    Ullah, Imtiaz
    Ullah, Ayaz
    Sajjad, Mazhar
    IOT, 2021, 2 (03): : 428 - 448
  • [5] Deep Graph Learning for Anomalous Citation Detection
    Liu, Jiaying
    Xia, Feng
    Feng, Xu
    Ren, Jing
    Liu, Huan
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (06) : 2543 - 2557
  • [6] Deep learning for anomaly detection in log data: A survey
    Landauer, Max
    Onder, Sebastian
    Skopik, Florian
    Wurzenberger, Markus
    MACHINE LEARNING WITH APPLICATIONS, 2023, 12
  • [7] Deep learning for anomaly detection in log data: A survey
    Landauer, Max
    Onder, Sebastian
    Skopik, Florian
    Wurzenberger, Markus
    MACHINE LEARNING WITH APPLICATIONS, 2023, 12
  • [8] Anomalous Subgraph Detection in Given Expected Degree Networks With Deep Learning
    Luan, Mingan
    Wang, Bo
    Zhao, Yanping
    Hu, Fengye
    IEEE ACCESS, 2021, 9 : 60052 - 60062
  • [9] A Survey of Android Malware Detection with Deep Neural Models
    Qiu, Junyang
    Zhang, Jun
    Luo, Wei
    Pan, Lei
    Nepal, Surya
    Xiang, Yang
    ACM COMPUTING SURVEYS, 2021, 53 (06)
  • [10] Deep Transfer Learning for IoT Attack Detection
    Vu, Ly
    Quang Uy Nguyen
    Nguyen, Diep N.
    Dinh Thai Hoang
    Dutkiewicz, Eryk
    IEEE ACCESS, 2020, 8 : 107335 - 107344