Zobrazeno 1 - 10
of 3 395
pro vyhledávání: '"SUN, Nan"'
DNN-based watermarking methods have rapidly advanced, with the ``Encoder-Noise Layer-Decoder'' (END) framework being the most widely used. To ensure end-to-end training, the noise layer in the framework must be differentiable. However, real-world dis
Externí odkaz:
http://arxiv.org/abs/2412.09960
In the rapidly evolving domain of Artificial Intelligence (AI), the complex interaction between innovation and regulation has become an emerging focus of our society. Despite tremendous advancements in AI's capabilities to excel in specific tasks and
Externí odkaz:
http://arxiv.org/abs/2412.04683
Nowadays, software development progresses rapidly to incorporate new features. To facilitate such growth and provide convenience for developers when creating and updating software, reusing open-source software (i.e., thirdparty library reuses) has be
Externí odkaz:
http://arxiv.org/abs/2411.19648
The increasing demand for intelligent assistants in human-populated environments has motivated significant research in autonomous robotic systems. Traditional service robots and virtual assistants, however, struggle with real-world task execution due
Externí odkaz:
http://arxiv.org/abs/2409.17655
Digital watermarking is the process of embedding secret information by altering images in an undetectable way to the human eye. To increase the robustness of the model, many deep learning-based watermarking methods use the encoder-noise-decoder archi
Externí odkaz:
http://arxiv.org/abs/2405.05170
Modern image processing tools have made it easy for attackers to crop the region or object of interest in images and paste it into other images. The challenge this cropping-paste attack poses to the watermarking technology is that it breaks the synch
Externí odkaz:
http://arxiv.org/abs/2405.03458
Embedding invisible hyperlinks or hidden codes in images to replace QR codes has become a hot topic recently. This technology requires first localizing the embedded region in the captured photos before decoding. Existing methods that train models to
Externí odkaz:
http://arxiv.org/abs/2405.03436
Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information from t
Externí odkaz:
http://arxiv.org/abs/2403.15779
Autor:
Mo, Xiaoxing, Zhang, Yechao, Zhang, Leo Yu, Luo, Wei, Sun, Nan, Hu, Shengshan, Gao, Shang, Xiang, Yang
A backdoor attack in deep learning inserts a hidden backdoor in the model to trigger malicious behavior upon specific input patterns. Existing detection approaches assume a metric space (for either the original inputs or their latent representations)
Externí odkaz:
http://arxiv.org/abs/2312.02673
Autor:
Li, Bo-Rui1,2 (AUTHOR), Sun, Nan1 (AUTHOR), Xu, Ming-Shan3 (AUTHOR), Sun, Qi-Xing1 (AUTHOR), Wang, Hui-Ming2 (AUTHOR), Zhou, Jie2 (AUTHOR), Luo, Xu1 (AUTHOR) luoxu@nbu.edu.cn, Lv, Guang-Hui2 (AUTHOR), Yang, Xiao-Dong1,2 (AUTHOR) xjyangxd@sina.com
Publikováno v:
PLoS ONE. 12/6/2024, Vol. 19 Issue 12, p1-21. 21p.
