Adversarial Machine Learning: Attacks, Defenses, and Open Challenges
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929705796501504 |
|---|---|
| author | Jha, Pranav K |
| author_facet | Jha, Pranav K |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05637 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adversarial Machine Learning: Attacks, Defenses, and Open Challenges Jha, Pranav K Cryptography and Security Artificial Intelligence 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. |
| title | Adversarial Machine Learning: Attacks, Defenses, and Open Challenges |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2502.05637 |