Corpus ID: 231583084

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning

@article{Nasr2021AdversaryIL,
  title={Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning},
  author={Milad Nasr and Shuang Song and Abhradeep Thakurta and Nicolas Papernot and Nicholas Carlini},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.04535}
}
Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a dataset D, or a dataset D′ that differs in just one example. If observing the training algorithm does not meaningfully increase the adversary’s odds of successfully guessing which dataset the model was trained on, then the algorithm is said to be differentially… Expand
4 Citations

Figures and Tables from this paper

Membership Inference Attacks on Machine Learning: A Survey
  • PDF
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
  • 1
  • PDF

References

SHOWING 1-10 OF 57 REFERENCES
Evaluating Differentially Private Machine Learning in Practice
  • 107
  • PDF
Membership Inference Attacks Against Machine Learning Models
  • 978
  • PDF
Exploiting Unintended Feature Leakage in Collaborative Learning
  • 277
  • PDF
Differentially Private Empirical Risk Minimization
  • 826
  • PDF
Auditing Differentially Private Machine Learning: How Private is Private SGD?
  • 14
  • Highly Influential
  • PDF
Label-Only Membership Inference Attacks
  • 13
  • PDF
Scalable Private Learning with PATE
  • 203
  • PDF
Towards Practical Differentially Private Convex Optimization
  • 49
  • PDF
Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds
  • 392
  • Highly Influential
  • PDF
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
  • 187
  • PDF
...
1
2
3
4
5
...