Semantic Scholar Open Access 2016 7457 sitasi

Deep Learning with Differential Privacy

Martín Abadi Andy Chu I. Goodfellow H. B. McMahan Ilya Mironov +2 lainnya

Lihat Sumber DOI

Abstrak

Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models should not expose private information in these datasets. Addressing this goal, we develop new algorithmic techniques for learning and a refined analysis of privacy costs within the framework of differential privacy. Our implementation and experiments demonstrate that we can train deep neural networks with non-convex objectives, under a modest privacy budget, and at a manageable cost in software complexity, training efficiency, and model quality.

Topik & Kata Kunci

Computer Science Mathematics

Penulis (7)

Martín Abadi

Andy Chu

I. Goodfellow

H. B. McMahan

Ilya Mironov

Kunal Talwar

Li Zhang

Format Sitasi

APA MLA BibTeX

Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K. et al. (2016). Deep Learning with Differential Privacy. https://doi.org/10.1145/2976749.2978318

Akses Cepat

Lihat di Sumber doi.org/10.1145/2976749.2978318

Informasi Jurnal

Tahun Terbit: 2016
Bahasa: en
Total Sitasi: 7457×
Sumber Database: Semantic Scholar
DOI: 10.1145/2976749.2978318
Akses: Open Access ✓