The answer lies within: Detecting Trojans from DNNs' inherent characteristics
文献类型：期刊论文
| 作者 | Liu, Xuchao; Cao, Qi; Zhang, Kaike; Su, Du; Shen, Huawei |
| 刊名 | NEURAL NETWORKS
 |
| 出版日期 | 2026-06-01 |
| 卷号 | 198页码:11 |
| 关键词 | Trojan detection Sample-free DNNs' inherent characteristics |
| ISSN号 | 0893-6080 |
| DOI | 10.1016/j.neunet.2026.108573 |
| 英文摘要 | Deep neural networks (DNNs) are vulnerable to Trojan attacks, where adversaries implant Trojans that cause DNNs to misbehave when encountering specific triggers. Detecting Trojans in DNNs is crucial to mitigate potential safety risks. Traditional methods typically employ trigger reversion techniques, which utilize benign samples to reconstruct potential triggers through iterative optimization. However, their practical applicability is limited by reliance on benign samples and the exceedingly time-intensive optimization. In this paper, we investigate more general yet challenging setting, the benign sample-free scenario, where detection relies solely on DNN itself. We propose a novel approach for detecting Trojans from DNNs' inherent characteristics (DTIC), which exploits the distinguishable features of Trojaned models. DTIC depicts the characteristics of various DNNs via a unified representation space derived from both views of model structures and parameters, enabling adaptability across diverse DNNs. It requires just one direct inference to assess the presence of Trojans, ensuring high efficiency. We further enhance the performance of Trojan detection, using augmentations based on random perturbations and the lottery hypothesis. Extensive experiments conducted on IARPA TrajAI1, a widely adopted benchmark, demonstrate the superior effectiveness, efficiency, and generalizability of DTIC. |
| 资助项目 | National Key R&D Program of China[2022YFB3103700] ; National Key R&D Program of China[2022YFB3103701] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0680101] ; National Natural Science Foundation of China[62472409] |
| WOS研究方向 | Computer Science ; Neurosciences & Neurology |
| 语种 | 英语 |
| WOS记录号 | WOS:001668510200001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42843]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Cao, Qi |
| 作者单位 | Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Xuchao,Cao, Qi,Zhang, Kaike,et al. The answer lies within: Detecting Trojans from DNNs' inherent characteristics[J]. NEURAL NETWORKS,2026,198:11. |
| APA | Liu, Xuchao,Cao, Qi,Zhang, Kaike,Su, Du,&Shen, Huawei.(2026).The answer lies within: Detecting Trojans from DNNs' inherent characteristics.NEURAL NETWORKS,198,11. |
| MLA | Liu, Xuchao,et al."The answer lies within: Detecting Trojans from DNNs' inherent characteristics".NEURAL NETWORKS 198(2026):11. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。