FBA$^2$D: Frequency-based Black-box Attack for AI-generated Image Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909953559625728 |
|---|---|
| author | Chen, Xiaojing Li, Dan Peng, Lijun YanŁetter, Jun Guo, Zhiqing Chen, Junyang Lan, Xiao Ba, Zhongjie DiaoŁetter, Yunfeng |
| author_facet | Chen, Xiaojing Li, Dan Peng, Lijun YanŁetter, Jun Guo, Zhiqing Chen, Junyang Lan, Xiao Ba, Zhongjie DiaoŁetter, Yunfeng |
| contents | The prosperous development of Artificial Intelligence-Generated Content (AIGC) has brought people's anxiety about the spread of false information on social media. Designing detectors for filtering is an effective defense method, but most detectors will be compromised by adversarial samples. Currently, most studies exposing AIGC security issues assume information on model structure and data distribution. In real applications, attackers query and interfere with models that provide services in the form of application programming interfaces (APIs), which constitutes the black-box decision-based attack paradigm. However, to the best of our knowledge, decision-based attacks on AIGC detectors remain unexplored. In this study, we propose \textbf{FBA$^2$D}: a frequency-based black-box attack method for AIGC detection to fill the research gap. Motivated by frequency-domain discrepancies between generated and real images, we develop a decision-based attack that leverages the Discrete Cosine Transform (DCT) for fine-grained spectral partitioning and selects frequency bands as query subspaces, improving both query efficiency and image quality. Moreover, attacks on AIGC detectors should mitigate initialization failures, preserve image quality, and operate under strict query budgets. To address these issues, we adopt an ``adversarial example soup'' method, averaging candidates from successive surrogate iterations and using the result as the initialization to accelerate the query-based attack. The empirical study on the Synthetic LSUN dataset and GenImage dataset demonstrate the effectiveness of our prosed method. This study shows the urgency of addressing practical AIGC security problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09264 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FBA$^2$D: Frequency-based Black-box Attack for AI-generated Image Detection Chen, Xiaojing Li, Dan Peng, Lijun YanŁetter, Jun Guo, Zhiqing Chen, Junyang Lan, Xiao Ba, Zhongjie DiaoŁetter, Yunfeng Cryptography and Security Artificial Intelligence The prosperous development of Artificial Intelligence-Generated Content (AIGC) has brought people's anxiety about the spread of false information on social media. Designing detectors for filtering is an effective defense method, but most detectors will be compromised by adversarial samples. Currently, most studies exposing AIGC security issues assume information on model structure and data distribution. In real applications, attackers query and interfere with models that provide services in the form of application programming interfaces (APIs), which constitutes the black-box decision-based attack paradigm. However, to the best of our knowledge, decision-based attacks on AIGC detectors remain unexplored. In this study, we propose \textbf{FBA$^2$D}: a frequency-based black-box attack method for AIGC detection to fill the research gap. Motivated by frequency-domain discrepancies between generated and real images, we develop a decision-based attack that leverages the Discrete Cosine Transform (DCT) for fine-grained spectral partitioning and selects frequency bands as query subspaces, improving both query efficiency and image quality. Moreover, attacks on AIGC detectors should mitigate initialization failures, preserve image quality, and operate under strict query budgets. To address these issues, we adopt an ``adversarial example soup'' method, averaging candidates from successive surrogate iterations and using the result as the initialization to accelerate the query-based attack. The empirical study on the Synthetic LSUN dataset and GenImage dataset demonstrate the effectiveness of our prosed method. This study shows the urgency of addressing practical AIGC security problems. |
| title | FBA$^2$D: Frequency-based Black-box Attack for AI-generated Image Detection |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2512.09264 |