Skip to main content

> ML_LITERATURE // ABADI-2016-DEEP-LEARNING-WITH-DIFFERENTIAL-PRIVACY_v1.0

Deep Learning with Differential Privacy (DP-SGD)

Martin Abadi, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang · ACM SIGSAC Conference on Computer and Communications Security (CCS) (2016)

safety-fairness2016industry-standardartifactsAvailable
DOI: 10.1145/2976749.2978318Back to Literature

Principal Contribution

Introduced Differentially Private SGD (DP-SGD) with per-sample gradient clipping and calibrated Gaussian noise injection with Moments Accountant.

Operational Relevance

Directly guides deployment choices and architecture selection for task-privacy-preserving-ml.

Assumptions

  • Standard empirical regularity and statistical stability hold across evaluation domains

Limitations

  • Performance characteristics depend on domain distribution and compute allocation parameters

Connected Algorithms, Architectures & Tools

Related Algorithms:
Related Architectures:
Implementing Libraries: