Adversarial Machine Learning: Attacks, Defenses, and Open Challenges

Pranav K Jha
2/8/2025
cs.CRcs.AI

No confident code implementation found for this paper. 5 possible matches can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Targeted Adversarial Traffic Generation : Black-box Approach to Evade Intrusion Detection Systems in IoT Networks

86% match2026

Recent Advances in Attack and Defense Approaches of Large Language Models

86% match2024

Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare

85% match2024

Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management

85% match2024

LLbezpeky: Leveraging Large Language Models for Vulnerability Detection

85% match2024

Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities

84% match2024

Cite this paper

@article{jha2025adversarial,
  title  = {Adversarial Machine Learning: Attacks, Defenses, and Open Challenges},
  author = {Pranav K Jha},
  year   = {2025},
  eprint = {2502.05637},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.05637v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.05637.svg)](https://codeofpaper.com/paper/2502.05637)

Discussion