Anomalous Example Detection in Deep Learning: A Survey
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9144212/ |
| _version_ | 1811274122880090112 |
|---|---|
| author | Saikiran Bulusu Bhavya Kailkhura Bo Li Pramod K. Varshney Dawn Song |
| author_facet | Saikiran Bulusu Bhavya Kailkhura Bo Li Pramod K. Varshney Dawn Song |
| author_sort | Saikiran Bulusu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-12T23:12:10Z |
| format | Article |
| id | doaj.art-e1b88a9ca7a84c9899447a975bdb1e5d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T23:12:10Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e1b88a9ca7a84c9899447a975bdb1e5d2022-12-22T03:12:46ZengIEEEIEEE Access2169-35362020-01-01813233013234710.1109/ACCESS.2020.30102749144212Anomalous Example Detection in Deep Learning: A SurveySaikiran Bulusu0https://orcid.org/0000-0002-4594-4844Bhavya Kailkhura1https://orcid.org/0000-0002-2819-2919Bo Li2Pramod K. Varshney3https://orcid.org/0000-0003-4504-5088Dawn Song4EECS Department, Syracuse University, Syracuse, NY, USALawrence Livermore National Laboratory, Livermore, CA, USAComputer Science Department, University of Illinois at Urbana--Champaign, Champaign IL, USAEECS Department, Syracuse University, Syracuse, NY, USAEECS Department, University of California at Berkeley, Berkeley, CA, USADeep 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.https://ieeexplore.ieee.org/document/9144212/Anomaly detectionout-of-distributionadversarial examplesdeep learningneural network |
| spellingShingle | Saikiran Bulusu Bhavya Kailkhura Bo Li Pramod K. Varshney Dawn Song Anomalous Example Detection in Deep Learning: A Survey IEEE Access Anomaly detection out-of-distribution adversarial examples deep learning neural network |
| title | Anomalous Example Detection in Deep Learning: A Survey |
| title_full | Anomalous Example Detection in Deep Learning: A Survey |
| title_fullStr | Anomalous Example Detection in Deep Learning: A Survey |
| title_full_unstemmed | Anomalous Example Detection in Deep Learning: A Survey |
| title_short | Anomalous Example Detection in Deep Learning: A Survey |
| title_sort | anomalous example detection in deep learning a survey |
| topic | Anomaly detection out-of-distribution adversarial examples deep learning neural network |
| url | https://ieeexplore.ieee.org/document/9144212/ |
| work_keys_str_mv | AT saikiranbulusu anomalousexampledetectionindeeplearningasurvey AT bhavyakailkhura anomalousexampledetectionindeeplearningasurvey AT boli anomalousexampledetectionindeeplearningasurvey AT pramodkvarshney anomalousexampledetectionindeeplearningasurvey AT dawnsong anomalousexampledetectionindeeplearningasurvey |