A Comprehensive Review of Adversarial Attacks on Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahmed, Syed Quiser, Ganesh, Bharathi Vokkaliga, Kumar, Sathyanarayana Sampath, Mishra, Prakhar, Anand, Ravi, Akurathi, Bhanuteja
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916525345079296
author Ahmed, Syed Quiser
Ganesh, Bharathi Vokkaliga
Kumar, Sathyanarayana Sampath
Mishra, Prakhar
Anand, Ravi
Akurathi, Bhanuteja
author_facet Ahmed, Syed Quiser
Ganesh, Bharathi Vokkaliga
Kumar, Sathyanarayana Sampath
Mishra, Prakhar
Anand, Ravi
Akurathi, Bhanuteja
contents This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and future research directions. To gain practical insights, we employ the Adversarial Robustness Toolbox (ART) [1] library to simulate these attacks on real-world use cases, such as self-driving cars. Our goal is to inform practitioners and researchers about the challenges and opportunities in defending AI systems against adversarial threats. By providing a comprehensive comparison of different attack methods, we aim to contribute to the development of more robust and secure AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11384
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Comprehensive Review of Adversarial Attacks on Machine Learning
Ahmed, Syed Quiser
Ganesh, Bharathi Vokkaliga
Kumar, Sathyanarayana Sampath
Mishra, Prakhar
Anand, Ravi
Akurathi, Bhanuteja
Cryptography and Security
This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and future research directions. To gain practical insights, we employ the Adversarial Robustness Toolbox (ART) [1] library to simulate these attacks on real-world use cases, such as self-driving cars. Our goal is to inform practitioners and researchers about the challenges and opportunities in defending AI systems against adversarial threats. By providing a comprehensive comparison of different attack methods, we aim to contribute to the development of more robust and secure AI systems.
title A Comprehensive Review of Adversarial Attacks on Machine Learning
topic Cryptography and Security
url https://arxiv.org/abs/2412.11384