Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917618080808960 |
|---|---|
| author | Zhao, Jingke Wang, Zan Wang, Yongwei Wang, Lanjun |
| author_facet | Zhao, Jingke Wang, Zan Wang, Yongwei Wang, Lanjun |
| contents | Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their threats in practice, or perform visually noticeable in stealthiness. Besides, there is still room to improve the attack success rates in the scenario that different poisoned samples may have different target labels (a.k.a., the all-to-all setting). In this study, we propose a novel imperceptible backdoor attack framework, named Impart, in the scenario where the attacker has no access to the victim model. Specifically, in order to enhance the attack capability of the all-to-all setting, we first propose a label-specific attack. Different from previous works which try to find an imperceptible pattern and add it to the source image as the poisoned image, we then propose to generate perturbations that align with the target label in the image feature by a surrogate model. In this way, the generated poisoned images are attached with knowledge about the target class, which significantly enhances the attack capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13017 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Impart: An Imperceptible and Effective Label-Specific Backdoor Attack Zhao, Jingke Wang, Zan Wang, Yongwei Wang, Lanjun Cryptography and Security Artificial Intelligence Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their threats in practice, or perform visually noticeable in stealthiness. Besides, there is still room to improve the attack success rates in the scenario that different poisoned samples may have different target labels (a.k.a., the all-to-all setting). In this study, we propose a novel imperceptible backdoor attack framework, named Impart, in the scenario where the attacker has no access to the victim model. Specifically, in order to enhance the attack capability of the all-to-all setting, we first propose a label-specific attack. Different from previous works which try to find an imperceptible pattern and add it to the source image as the poisoned image, we then propose to generate perturbations that align with the target label in the image feature by a surrogate model. In this way, the generated poisoned images are attached with knowledge about the target class, which significantly enhances the attack capability. |
| title | Impart: An Imperceptible and Effective Label-Specific Backdoor Attack |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2403.13017 |