Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2412.16234 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913622533341184 |
|---|---|
| author | Zhang, Jun-Jie Song, Jiahao Wang, Xiu-Cheng Li, Fu-Peng Liu, Zehan Chen, Jian-Nan Dang, Haoning Wang, Shiyao Zhang, Yiyan Xu, Jianhui Shi, Chunxiang Wang, Fei Pang, Long-Gang Cheng, Nan Zhang, Weiwei Zhang, Duo Meng, Deyu |
| author_facet | Zhang, Jun-Jie Song, Jiahao Wang, Xiu-Cheng Li, Fu-Peng Liu, Zehan Chen, Jian-Nan Dang, Haoning Wang, Shiyao Zhang, Yiyan Xu, Jianhui Shi, Chunxiang Wang, Fei Pang, Long-Gang Cheng, Nan Zhang, Weiwei Zhang, Duo Meng, Deyu |
| contents | We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant deviations in their outputs. Through an analysis of five diverse application areas -- weather forecasting, chemical energy and force calculations, fluid dynamics, quantum chromodynamics, and wireless communication -- we demonstrate that this vulnerability is a broad and general characteristic of AI systems. This revelation exposes a hidden risk in relying on neural networks for essential scientific computations, calling further studies on their reliability and security. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16234 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Is AI Robust Enough for Scientific Research? Zhang, Jun-Jie Song, Jiahao Wang, Xiu-Cheng Li, Fu-Peng Liu, Zehan Chen, Jian-Nan Dang, Haoning Wang, Shiyao Zhang, Yiyan Xu, Jianhui Shi, Chunxiang Wang, Fei Pang, Long-Gang Cheng, Nan Zhang, Weiwei Zhang, Duo Meng, Deyu Machine Learning Computational Physics We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant deviations in their outputs. Through an analysis of five diverse application areas -- weather forecasting, chemical energy and force calculations, fluid dynamics, quantum chromodynamics, and wireless communication -- we demonstrate that this vulnerability is a broad and general characteristic of AI systems. This revelation exposes a hidden risk in relying on neural networks for essential scientific computations, calling further studies on their reliability and security. |
| title | Is AI Robust Enough for Scientific Research? |
| topic | Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2412.16234 |