Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912368892575744 |
|---|---|
| author | Wang, Guangjing Zhou, Ce Wang, Yuanda Chen, Bocheng Guo, Hanqing Yan, Qiben |
| author_facet | Wang, Guangjing Zhou, Ce Wang, Yuanda Chen, Bocheng Guo, Hanqing Yan, Qiben |
| contents | As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to generalize across instances, domains, models, tasks, modalities, or even hardware platforms, pose severe risks to security, privacy, and system integrity. This survey delivers the first comprehensive review of transferable attacks across seven major categories, including evasion, backdoor, data poisoning, model stealing, model inversion, membership inference, and side-channel attacks. We introduce a unified six-dimensional taxonomy: cross-instance, cross-domain, cross-modality, cross-model, cross-task, and cross-hardware, which systematically captures the diverse transfer pathways of adversarial strategies. Through this framework, we examine both the underlying mechanics and practical implications of transferable attacks on AI systems. Furthermore, we review cutting-edge methods for enhancing attack transferability, organized around data augmentation and optimization strategies. By consolidating fragmented research and identifying critical future directions, this work provides a foundational roadmap for understanding, evaluating, and defending against transferable threats in real-world AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_11796 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems Wang, Guangjing Zhou, Ce Wang, Yuanda Chen, Bocheng Guo, Hanqing Yan, Qiben Cryptography and Security Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to generalize across instances, domains, models, tasks, modalities, or even hardware platforms, pose severe risks to security, privacy, and system integrity. This survey delivers the first comprehensive review of transferable attacks across seven major categories, including evasion, backdoor, data poisoning, model stealing, model inversion, membership inference, and side-channel attacks. We introduce a unified six-dimensional taxonomy: cross-instance, cross-domain, cross-modality, cross-model, cross-task, and cross-hardware, which systematically captures the diverse transfer pathways of adversarial strategies. Through this framework, we examine both the underlying mechanics and practical implications of transferable attacks on AI systems. Furthermore, we review cutting-edge methods for enhancing attack transferability, organized around data augmentation and optimization strategies. By consolidating fragmented research and identifying critical future directions, this work provides a foundational roadmap for understanding, evaluating, and defending against transferable threats in real-world AI systems. |
| title | Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems |
| topic | Cryptography and Security Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.11796 |