Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)

<Previous Article In Volume
Next Article In Volume>

Adversaries on ML Models: The Dark side of Learning

Authors
Sahithi Godavarthi1, 2, *, G. Venkateswara Rao3
1Research Scholar, Dept. of CSE, GITAM School of Technology, GITAM (Deemed to Be University), Visakhapatnam, India
2Assistant Professor, Department of Emerging Technologies, CVR College of Engineering, Hyderabad, India
3Professor, Dept. of CSE, GITAM School of Technology, GITAM (Deemed to Be University), Visakhapatnam, India
*Corresponding author. Email: sahithi.godavarthi@gmail.com
Corresponding Author
Sahithi Godavarthi
Available Online 30 July 2024.
DOI
10.2991/978-94-6463-471-6_124How to use a DOI?
Keywords
Adversary; Resilient; Mitigate; Counter measures; Safe guarding ML
Abstract

Today's technological trends are advancing to new levels and showing a diverse array of uses. One of these that has recently grown in prominence is machine learning. The ability of ML to analyze data, learn, make decisions and predictions made it the outstanding technology to be used in plentiful of gadgets. Conversely, adversaries also affect ML models in different phases. One challenge for ML users is therefore to make the models robust before using them in applications. The focus of this work is on the several hostile scenarios that machine learning models encounter and the countermeasures that can be taken to lessen the opponents’ influence. There is a need for study that concentrates on creating stronger defenses against assaults on ML models. This paper can provide a full overview of machine learning (ML) and its history. It also outlines future research possibilities for securing ML models.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
Series
Advances in Computer Science Research
Publication Date
30 July 2024
ISBN
978-94-6463-471-6
ISSN
2352-538X
DOI
10.2991/978-94-6463-471-6_124How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Sahithi Godavarthi
AU  - G. Venkateswara Rao
PY  - 2024
DA  - 2024/07/30
TI  - Adversaries on ML Models: The Dark side of Learning
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 1294
EP  - 1303
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_124
DO  - 10.2991/978-94-6463-471-6_124
ID  - Godavarthi2024
ER  -