paper-with-me

홈 › Papers

Disparate Impact in Differential Privacy from Gradient Misalignment

2022-06-15 · Maria S. Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, Jesse C. Cresswell

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.

📄 PDF Abstract BibTeX arXiv:2206.07737

Code (1)

layer6ai-labs/fair-dp 공식 구현 pytorch

Tasks

Fairness

Methods 이 논문이 사용한 방법론

Gradient Clipping One difficulty that arises with optimization of deep neural networks is that large parameter gradients can lead an SGD optimizer to update…

Similar Papers 제목 키워드 기반

Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy

2020-03-08 · Depeng Xu, Wei Du, Xintao Wu

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

2025-10-02 · Lea Demelius, Dominik Kowald, Simone Kopeinik, Roman Kern 외 arxiv

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

2025-06-02 · Linzh Zhao, Aki Rehn, Mikko A. Heikkilä, Razane Tajeddine 외

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 Preserving

DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?

2021-06-22 · Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh 외

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 LearningFairness

Differential Privacy Has Disparate Impact on Model Accuracy

2019-05-28 · NeurIPS 2019 12 · Eugene Bagdasaryan, Vitaly Shmatikov

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