Stealthy Sensor Attacks Against Direct Data-Driven Controllers
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911469053935616 |
|---|---|
| author | Anand, Sribalaji C. |
| author_facet | Anand, Sribalaji C. |
| contents | This paper investigates the vulnerability of discrete-time linear time-invariant systems to stealthy sensor attacks during the learning phase. In particular, we demonstrate that a {data-driven} adversary, without access to the system model, can inject attacks that mislead the operator into learning an {unstable} state-feedback controller. We further analyze attacks that degrade the performance of data-driven ${H}_2$ controllers, while ensuring that the operator can always compute a feasible controller. Potential mitigation strategies are also discussed. Numerical examples illustrate the effectiveness of the proposed attacks and underscore the importance of accounting for adversarial manipulations in data-driven controller design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stealthy Sensor Attacks Against Direct Data-Driven Controllers Anand, Sribalaji C. Systems and Control This paper investigates the vulnerability of discrete-time linear time-invariant systems to stealthy sensor attacks during the learning phase. In particular, we demonstrate that a {data-driven} adversary, without access to the system model, can inject attacks that mislead the operator into learning an {unstable} state-feedback controller. We further analyze attacks that degrade the performance of data-driven ${H}_2$ controllers, while ensuring that the operator can always compute a feasible controller. Potential mitigation strategies are also discussed. Numerical examples illustrate the effectiveness of the proposed attacks and underscore the importance of accounting for adversarial manipulations in data-driven controller design. |
| title | Stealthy Sensor Attacks Against Direct Data-Driven Controllers |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2504.17347 |