Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910975893962752 |
|---|---|
| author | Zhang, Ruixuan Wang, He Zhao, Zhengyu Guo, Zhiqing Yang, Xun Diao, Yunfeng Wang, Meng |
| author_facet | Zhang, Ruixuan Wang, He Zhao, Zhengyu Guo, Zhiqing Yang, Xun Diao, Yunfeng Wang, Meng |
| contents | Rapid advances in Artificial Intelligence Generated Images (AIGI) have facilitated malicious use, such as forgery and misinformation. Therefore, numerous methods have been proposed to detect fake images. Although such detectors have been proven to be universally vulnerable to adversarial attacks, defenses in this field are scarce. In this paper, we first identify that adversarial training (AT), widely regarded as the most effective defense, suffers from performance collapse in AIGI detection. Through an information-theoretic lens, we further attribute the cause of collapse to feature entanglement, which disrupts the preservation of feature-label mutual information. Instead, standard detectors show clear feature separation. Motivated by this difference, we propose Training-free Robust Detection via Information-theoretic Measures (TRIM), the first training-free adversarial defense for AIGI detection. TRIM builds on standard detectors and quantifies feature shifts using prediction entropy and KL divergence. Extensive experiments across multiple datasets and attacks validate the superiority of our TRIM, e.g., outperforming the state-of-the-art defense by 33.88% (28.91%) on ProGAN (GenImage), while well maintaining original accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22604 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective Zhang, Ruixuan Wang, He Zhao, Zhengyu Guo, Zhiqing Yang, Xun Diao, Yunfeng Wang, Meng Computer Vision and Pattern Recognition Rapid advances in Artificial Intelligence Generated Images (AIGI) have facilitated malicious use, such as forgery and misinformation. Therefore, numerous methods have been proposed to detect fake images. Although such detectors have been proven to be universally vulnerable to adversarial attacks, defenses in this field are scarce. In this paper, we first identify that adversarial training (AT), widely regarded as the most effective defense, suffers from performance collapse in AIGI detection. Through an information-theoretic lens, we further attribute the cause of collapse to feature entanglement, which disrupts the preservation of feature-label mutual information. Instead, standard detectors show clear feature separation. Motivated by this difference, we propose Training-free Robust Detection via Information-theoretic Measures (TRIM), the first training-free adversarial defense for AIGI detection. TRIM builds on standard detectors and quantifies feature shifts using prediction entropy and KL divergence. Extensive experiments across multiple datasets and attacks validate the superiority of our TRIM, e.g., outperforming the state-of-the-art defense by 33.88% (28.91%) on ProGAN (GenImage), while well maintaining original accuracy. |
| title | Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.22604 |