Evasion Attacks Against Bayesian Predictive Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911000167448576 |
|---|---|
| author | Arce, Pablo G. Naveiro, Roi Insua, David Ríos |
| author_facet | Arce, Pablo G. Naveiro, Roi Insua, David Ríos |
| contents | There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning attacks to predictive models in classical setups, with the susceptibility of Bayesian predictive models to attacks remaining underexplored. This paper introduces a general methodology for designing optimal evasion attacks against such models. We investigate two adversarial objectives: perturbing specific point predictions and altering the entire posterior predictive distribution. For both scenarios, we propose novel gradient-based attacks and study their implementation and properties in various computational setups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09640 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evasion Attacks Against Bayesian Predictive Models Arce, Pablo G. Naveiro, Roi Insua, David Ríos Machine Learning 68T37 There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning attacks to predictive models in classical setups, with the susceptibility of Bayesian predictive models to attacks remaining underexplored. This paper introduces a general methodology for designing optimal evasion attacks against such models. We investigate two adversarial objectives: perturbing specific point predictions and altering the entire posterior predictive distribution. For both scenarios, we propose novel gradient-based attacks and study their implementation and properties in various computational setups. |
| title | Evasion Attacks Against Bayesian Predictive Models |
| topic | Machine Learning 68T37 |
| url | https://arxiv.org/abs/2506.09640 |