Indiscriminate Data Poisoning Attacks on Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914679293476864 |
|---|---|
| author | Lu, Yiwei Kamath, Gautam Yu, Yaoliang |
| author_facet | Lu, Yiwei Kamath, Gautam Yu, Yaoliang |
| contents | Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning attacks and connect them with old and new algorithms for solving sequential Stackelberg games. By choosing an appropriate loss function for the attacker and optimizing with algorithms that exploit second-order information, we design poisoning attacks that are effective on neural networks. We present efficient implementations that exploit modern auto-differentiation packages and allow simultaneous and coordinated generation of tens of thousands of poisoned points, in contrast to existing methods that generate poisoned points one by one. We further perform extensive experiments that empirically explore the effect of data poisoning attacks on deep neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_09092 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Indiscriminate Data Poisoning Attacks on Neural Networks Lu, Yiwei Kamath, Gautam Yu, Yaoliang Machine Learning Cryptography and Security Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning attacks and connect them with old and new algorithms for solving sequential Stackelberg games. By choosing an appropriate loss function for the attacker and optimizing with algorithms that exploit second-order information, we design poisoning attacks that are effective on neural networks. We present efficient implementations that exploit modern auto-differentiation packages and allow simultaneous and coordinated generation of tens of thousands of poisoned points, in contrast to existing methods that generate poisoned points one by one. We further perform extensive experiments that empirically explore the effect of data poisoning attacks on deep neural networks. |
| title | Indiscriminate Data Poisoning Attacks on Neural Networks |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2204.09092 |