Disparate Impact in Differential Privacy from Gradient Misalignment
As machine learning becomes more widespread throughout society, aspects including data privacy and fairness must be carefully considered, and are crucial for deployment in highly regulated industries. Unfortunately, the application of privacy enhancing technologies can worsen unfair tendencies in models. In particular, one of the most widely used techniques for private model training, differentially private stochastic gradient descent (DPSGD), frequently intensifies disparate impact on groups within data. In this work we study the fine-grained causes of unfairness in DPSGD and identify gradient misalignment due to inequitable gradient clipping as the most significant source. This observation leads us to a new method for reducing unfairness by preventing gradient misalignment in DPSGD.
Code (1)
Tasks
FairnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy
When we enforce differential privacy in machine learning, the utility-privacy trade-off is different w.r.t. each group. Gradient clipping and random noise addition disproportionately affect underrepresented and complex c…
Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD
Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the m…
Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
Differential privacy (DP) has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often have disparate impacts on model predictions, e.g., for minority groups. Gr…
Privacy PreservingDP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on different sub-groups in the population, whi…
Deep LearningFairnessDifferential Privacy Has Disparate Impact on Model Accuracy
Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in th…
Gender ClassificationGeneral Classificationimage-classificationImage Classification+2