Untraceable DeepFakes via Traceable Fingerprint Elimination
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_ | 1866911092198866944 |
|---|---|
| author | Lai, Jiewei Zhang, Lan Tang, Chen Sun, Pengcheng Wang, Xinming Wang, Yunhao |
| author_facet | Lai, Jiewei Zhang, Lan Tang, Chen Sun, Pengcheng Wang, Xinming Wang, Yunhao |
| contents | Recent advancements in DeepFakes attribution technologies have significantly enhanced forensic capabilities, enabling the extraction of traces left by generative models (GMs) in images, making DeepFakes traceable back to their source GMs. Meanwhile, several attacks have attempted to evade attribution models (AMs) for exploring their limitations, calling for more robust AMs. However, existing attacks fail to eliminate GMs' traces, thus can be mitigated by defensive measures. In this paper, we identify that untraceable DeepFakes can be achieved through a multiplicative attack, which can fundamentally eliminate GMs' traces, thereby evading AMs even enhanced with defensive measures. We design a universal and black-box attack method that trains an adversarial model solely using real data, applicable for various GMs and agnostic to AMs. Experimental results demonstrate the outstanding attack capability and universal applicability of our method, achieving an average attack success rate (ASR) of 97.08\% against 6 advanced AMs on DeepFakes generated by 9 GMs. Even in the presence of defensive mechanisms, our method maintains an ASR exceeding 72.39\%. Our work underscores the potential challenges posed by multiplicative attacks and highlights the need for more robust AMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03067 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Untraceable DeepFakes via Traceable Fingerprint Elimination Lai, Jiewei Zhang, Lan Tang, Chen Sun, Pengcheng Wang, Xinming Wang, Yunhao Cryptography and Security Artificial Intelligence Recent advancements in DeepFakes attribution technologies have significantly enhanced forensic capabilities, enabling the extraction of traces left by generative models (GMs) in images, making DeepFakes traceable back to their source GMs. Meanwhile, several attacks have attempted to evade attribution models (AMs) for exploring their limitations, calling for more robust AMs. However, existing attacks fail to eliminate GMs' traces, thus can be mitigated by defensive measures. In this paper, we identify that untraceable DeepFakes can be achieved through a multiplicative attack, which can fundamentally eliminate GMs' traces, thereby evading AMs even enhanced with defensive measures. We design a universal and black-box attack method that trains an adversarial model solely using real data, applicable for various GMs and agnostic to AMs. Experimental results demonstrate the outstanding attack capability and universal applicability of our method, achieving an average attack success rate (ASR) of 97.08\% against 6 advanced AMs on DeepFakes generated by 9 GMs. Even in the presence of defensive mechanisms, our method maintains an ASR exceeding 72.39\%. Our work underscores the potential challenges posed by multiplicative attacks and highlights the need for more robust AMs. |
| title | Untraceable DeepFakes via Traceable Fingerprint Elimination |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2508.03067 |