Yutong Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yutong Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hewang Nie
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China
1 shared publication - Jin Li
Computer Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Songfeng Lu
Huazhong University of Science and Technology
1 shared publication - Wenyue Li
Hubei Yihua Group Co., Ltd., Yichang, China
1 shared publication - Yixiao Gong
School of Cyber Science & Engineering, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Ziqi Zhou
College of Computer Science, Chongqing University, Chongqing, China
1 shared publication
Latest Publications
- Open Access
- 17 September 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 217
FakeMark: gradient-guided false watermark claims via robust feature fusion
Model watermarking supports intellectual-property claims by verifying a model’s responses to a secret key set, but this behavior-only interface is vulnerable to fabricated evidence. This work presents FakeMark , a gradient-guided false-claim attack for image classifiers that uses a white-box surrogate but never queries or accesses the victim model during attack construction. Under a simplified linear decision-boundary model, targeted perturbations can acquire a nonzero component along the watermark-trigger direction; experiments on deep networks provide only conditional, setting-dependent support for this intuition. FakeMark caches selected convolutional and fully connected layer outputs from clean surrogate batches and injects them through stochastic multi-layer, channel-wise interpolation to improve transfer. Across 16 distinct architectures and an additional adversarially trained ResNet-50 checkpoint variant, over eight evaluated watermark variants, retrospective best-case behavioral target-label accuracy reaches 1.00 on CIFAR-10 and 0.99 on ImageNet. ImageNet transfer varies substantially across checkpoint and surrogate settings, ranging from near zero to 0.99. Matched baselines and detector analyses motivate provenance-aware, multi-factor ownership protocols.
- 17 September 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 217
Open AccessFakeMark: gradient-guided false watermark claims via robust feature fusion
Model watermarking supports intellectual-property claims by verifying a model’s responses to a secret key set, but this behavior-only interface is vulnerable to fabricated evidence. This work presents FakeMark , a gradient-guided false-claim attack for image classifiers that uses a white-box surrogate but never queries or accesses the victim model during attack construction. Under a simplified linear decision-boundary model, targeted perturbations can acquire a nonzero component along the watermark-trigger direction; experiments on deep networks provide only conditional, setting-dependent support for this intuition. FakeMark caches selected convolutional and fully connected layer outputs from clean surrogate batches and injects them through stochastic multi-layer, channel-wise interpolation to improve transfer. Across 16 distinct architectures and an additional adversarially trained ResNet-50 checkpoint variant, over eight evaluated watermark variants, retrospective best-case behavioral target-label accuracy reaches 1.00 on CIFAR-10 and 0.99 on ImageNet. ImageNet transfer varies substantially across checkpoint and surrogate settings, ranging from near zero to 0.99. Matched baselines and detector analyses motivate provenance-aware, multi-factor ownership protocols.