Adversarial Machine Learning: Attacks, Defenses, and Open Challenges

2025/02/08 by Jha, Pranav K
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2502.05637

Abstract

Adversarial Machine Learning (AML) addresses vulnerabilities in AI systems where adversaries manipulate inputs or training data to degrade performance. This article provides a comprehensive analysis of evasion and poisoning attacks, formalizes defense mechanisms with mathematical rigor, and discusses the challenges of implementing robust solutions in adaptive threat models. Additionally, it highlights open challenges in certified robustness, scalability, and real-world deployment.

Related

• Adversarial machine learning :
• Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
• You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks
• A Comprehensive Review of Adversarial Attacks on Machine Learning
• Defenses in Adversarial Machine Learning: A Survey