no code implementations • 21 Apr 2024 • Hongyu Zhu, Sichu Liang, Wentao Hu, Fangqi Li, Ju Jia, Shilin Wang
With the rise of Machine Learning as a Service (MLaaS) platforms, safeguarding the intellectual property of deep learning models is becoming paramount.
2 code implementations • 7 Apr 2024 • Zihan Liu, Hanyi Wang, Yaoyu Kang, Shilin Wang
Remarkably, our best-performing ViT-L/14 variant requires training only 0. 08% of its parameters to surpass the leading baseline by +3. 64% mAP and +12. 72% avg. Acc across unseen diffusion and autoregressive models.
no code implementations • 20 Feb 2024 • Fangqi Li, Haodong Zhao, Wei Du, Shilin Wang
To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark.
no code implementations • 7 Nov 2022 • Zihan Liu, Hanyi Wang, Shilin Wang
As ultra-realistic face forgery techniques emerge, deepfake detection has attracted increasing attention due to security concerns.
no code implementations • COLING 2022 • Yutao Luo, Menghua Lu, Gongshen Liu, Shilin Wang
To alleviate these problems, we propose a prompt-based approach, Prefix-Controlled Generator (i. e., PCG), for few-shot table-to-text generation.
1 code implementation • 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022) 2022 • Yichuan Mo, Shilin Wang
In this paper, by observing that deepening the network impairs the performance of the network in detecting unknown attacks, we propose that the synthetic speech detection problem is an out-of-distribution (OOD) generalization problem and we enhance the robustness of networks by using multi-task learning.
no code implementations • 9 Apr 2022 • Fangqi Li, Shilin Wang
To confront these challenges, we propose a knowledge-free black-box watermarking scheme for image classification neural networks.