Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917091040296960 |
|---|---|
| author | Domico, Kyle Ferrand, Jean-Charles Noirot Sheatsley, Ryan Pauley, Eric Hanna, Josiah McDaniel, Patrick |
| author_facet | Domico, Kyle Ferrand, Jean-Charles Noirot Sheatsley, Ryan Pauley, Eric Hanna, Josiah McDaniel, Patrick |
| contents | Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial samples. Unlike traditional adversarial machine learning (AML) methods that craft adversarial samples independently, our RL-based approach retains and exploits past attack experience to improve the effectiveness and efficiency of future attacks. We formulate adversarial sample generation as a Markov Decision Process and evaluate RL's ability to (a) learn effective and efficient attack strategies and (b) compete with state-of-the-art AML. On two image classification benchmarks, our agent increases attack success rate by up to 13.2% and decreases the average number of victim model queries per attack by up to 16.9% from the start to the end of training. In a head-to-head comparison with state-of-the-art image attacks, our approach enables an adversary to generate adversarial samples with 17% more success on unseen inputs post-training. From a security perspective, this work demonstrates a powerful new attack vector that uses RL to train agents that attack ML models efficiently and at scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning Domico, Kyle Ferrand, Jean-Charles Noirot Sheatsley, Ryan Pauley, Eric Hanna, Josiah McDaniel, Patrick Cryptography and Security Artificial Intelligence Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial samples. Unlike traditional adversarial machine learning (AML) methods that craft adversarial samples independently, our RL-based approach retains and exploits past attack experience to improve the effectiveness and efficiency of future attacks. We formulate adversarial sample generation as a Markov Decision Process and evaluate RL's ability to (a) learn effective and efficient attack strategies and (b) compete with state-of-the-art AML. On two image classification benchmarks, our agent increases attack success rate by up to 13.2% and decreases the average number of victim model queries per attack by up to 16.9% from the start to the end of training. In a head-to-head comparison with state-of-the-art image attacks, our approach enables an adversary to generate adversarial samples with 17% more success on unseen inputs post-training. From a security perspective, this work demonstrates a powerful new attack vector that uses RL to train agents that attack ML models efficiently and at scale. |
| title | Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2503.01734 |