The mathematics of adversarial attacks in AI – why deep learning is unstable despite the existence of stable neural networks.
Saved in:
| Title: | The mathematics of adversarial attacks in AI – why deep learning is unstable despite the existence of stable neural networks. |
|---|---|
| Authors: | Bastounis, Alexander1, Hansen, Anders2, ach70@cam.ac.uk, Vlačić, Verner3 |
| Source: | European Journal of Applied Mathematics; Feb2026, Vol. 37 Issue 1, p259-289, 31p |
| Database: | Applied Science & Technology Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| ISSN: | 09567925 |
|---|---|
| DOI: | 10.1017/S0956792525100193 |
