CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910861779533824 |
|---|---|
| author | Yang, Guangmingmei Li, Xi Wang, Hang Miller, David J. Kesidis, George |
| author_facet | Yang, Guangmingmei Li, Xi Wang, Hang Miller, David J. Kesidis, George |
| contents | A variety of defenses have been proposed against Trojans planted in (backdoor attacks on) deep neural network (DNN) classifiers. Backdoor-agnostic methods seek to reliably detect and/or to mitigate backdoors irrespective of the incorporation mechanism used by the attacker, while inversion methods explicitly assume one. In this paper, we describe a new detector that: relies on embedded feature representations to estimate (invert) the backdoor and to identify its target class; can operate without access to the training dataset; and is highly effective for various incorporation mechanisms (i.e., is backdoor agnostic). Our detection approach is evaluated -- and found to be favorable - in comparison with an array of published defenses for a variety of different attacks on the CIFAR-10 and CIFAR-100 image-classification domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors Yang, Guangmingmei Li, Xi Wang, Hang Miller, David J. Kesidis, George Cryptography and Security Machine Learning Neural and Evolutionary Computing A variety of defenses have been proposed against Trojans planted in (backdoor attacks on) deep neural network (DNN) classifiers. Backdoor-agnostic methods seek to reliably detect and/or to mitigate backdoors irrespective of the incorporation mechanism used by the attacker, while inversion methods explicitly assume one. In this paper, we describe a new detector that: relies on embedded feature representations to estimate (invert) the backdoor and to identify its target class; can operate without access to the training dataset; and is highly effective for various incorporation mechanisms (i.e., is backdoor agnostic). Our detection approach is evaluated -- and found to be favorable - in comparison with an array of published defenses for a variety of different attacks on the CIFAR-10 and CIFAR-100 image-classification domains. |
| title | CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors |
| topic | Cryptography and Security Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2402.02034 |