Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics
Abstract
In stock price forecasting, modeling the probabilistic dependence between stock prices within a time-series framework has remained a persistent and highly challenging area of research. We propose a novel model to explain the extreme co-movement in multivariate data with time-series dependencies. Our model incorporates a Hawkes process layer to capture abrupt co-movements, thereby enhancing the temporal representation of market dynamics. We introduce dynamic hypergraphs into our model adapting to higher-order (groupwise rather than pairwise) relationships within the stock market. Extensive experiments on real-world benchmarks demonstrate the robustness of our approach in predictive performance and portfolio stability.
Cite
Text
Wu et al. "Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/673Markdown
[Wu et al. "Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/wu2024ijcai-watermarks/) doi:10.24963/ijcai.2024/673BibTeX
@inproceedings{wu2024ijcai-watermarks,
title = {{Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics}},
author = {Wu, Xiaoshuai and Liao, Xin and Ou, Bo and Liu, Yuling and Qin, Zheng},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {6089-6097},
doi = {10.24963/ijcai.2024/673},
url = {https://mlanthology.org/ijcai/2024/wu2024ijcai-watermarks/}
}