Dawn: Dynamic adversarial watermarking of neural networks

S Szyller, BG Atli, S Marchal, N Asokan - Proceedings of the 29th ACM …, 2021 - dl.acm.org
Training machine learning (ML) models is expensive in terms of computational power,
amounts of labeled data and human expertise. Thus, ML models constitute business value …
被引用次数：162 相关文章

DAWN: Dynamic Adversarial Watermarking of Neural Networks

S Szyller, BG Atli, S Marchal… - … Conference on Multimedia, 2021 - research.aalto.fi
Training machine learning (ML) models is expensive in terms of computational power,
amounts of labeled data and human expertise. Thus, ML models constitute business value …
[PDF] researchgate.net

[PDF][PDF] DAWN: Dynamic Adversarial Watermarking of Neural Networks

S Szyller, BG Atli, S Marchal, N Asokan - researchgate.net
Training machine learning (ML) models is expensive in terms of computational power,
amounts of labeled data and human expertise. Thus, ML models constitute intellectual …

DAWN: Dynamic Adversarial Watermarking of Neural Networks

S Szyller, B Gul Atli, S Marchal, N Asokan - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
Training machine learning (ML) models is expensive in terms of computational power,
amounts of labeled data and human expertise. Thus, ML models constitute intellectual …

DAWN: Dynamic Adversarial Watermarking of Neural Networks

S Szyller, BG Atli, S Marchal, N Asokan - arXiv preprint arXiv:1906.00830, 2019 - arxiv.org
Training machine learning (ML) models is expensive in terms of computational power,
amounts of labeled data and human expertise. Thus, ML models constitute intellectual …