Fast and Lightweight Backdoor Detection via Head Random Probing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909054982422528 |
|---|---|
| author | Yu, Yinbo Yin, Xueyu Fang, Jing Tian, Chunwei Zhu, Qi Liu, Jiajia Zhang, Daoqiang |
| author_facet | Yu, Yinbo Yin, Xueyu Fang, Jing Tian, Chunwei Zhu, Qi Liu, Jiajia Zhang, Daoqiang |
| contents | Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data, gradients, or iterative trigger reconstruction, leading to high computational costs and limited robustness under practical model-auditing scenarios. In this paper, we propose HTell, a fast and lightweight data-free backdoor detector based on head random probing. Instead of reconstructing diverse trigger patterns, HTell inspects their unified manifestation in the prediction head: backdoored models tend to exhibit abnormal response concentration on the target class under random latent probes. HTell generates architecture-aware random latent probes, feeds them directly into the model head, and detects backdoors by analyzing class-wise response statistics, without accessing real or surrogate data, model gradients, or parameter optimization. We evaluate HTell on a large-scale benchmark containing more than 6,000 backdoored models and over 700 clean models, covering 4 datasets, 14 architectures, and 21 types of backdoor attacks. HTell achieves 99.03% true positive rate and 2.11% false positive rate with only 12.69 ms/model detection latency, reducing the time cost by over 30,000$\times$ compared with representative gradient-based detectors. These results demonstrate that head random probing provides an accurate, robust, and efficient solution for large-scale data-free backdoor model auditing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18908 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fast and Lightweight Backdoor Detection via Head Random Probing Yu, Yinbo Yin, Xueyu Fang, Jing Tian, Chunwei Zhu, Qi Liu, Jiajia Zhang, Daoqiang Cryptography and Security Artificial Intelligence Machine Learning Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data, gradients, or iterative trigger reconstruction, leading to high computational costs and limited robustness under practical model-auditing scenarios. In this paper, we propose HTell, a fast and lightweight data-free backdoor detector based on head random probing. Instead of reconstructing diverse trigger patterns, HTell inspects their unified manifestation in the prediction head: backdoored models tend to exhibit abnormal response concentration on the target class under random latent probes. HTell generates architecture-aware random latent probes, feeds them directly into the model head, and detects backdoors by analyzing class-wise response statistics, without accessing real or surrogate data, model gradients, or parameter optimization. We evaluate HTell on a large-scale benchmark containing more than 6,000 backdoored models and over 700 clean models, covering 4 datasets, 14 architectures, and 21 types of backdoor attacks. HTell achieves 99.03% true positive rate and 2.11% false positive rate with only 12.69 ms/model detection latency, reducing the time cost by over 30,000$\times$ compared with representative gradient-based detectors. These results demonstrate that head random probing provides an accurate, robust, and efficient solution for large-scale data-free backdoor model auditing. |
| title | Fast and Lightweight Backdoor Detection via Head Random Probing |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.18908 |