5 papers
Private and Stable Test-Time Adaptation with Differential Privacy
Zefeng Li, Qiaoyue Tang, Mathias Lecuyer +1
Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.…
FairNVT: Fair Classification via Noise Injection in Vision Transformers
Qiaoyue Tang, Sepidehsadat Hosseini, Mengyao Zhai +2
This paper presents FairNVT, a lightweight debiasing framework for pretrained transformer-based encoders that improves prediction fairness while preserving task performance. FairNV…
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance
Qiaoyue Tang, Alain Zhiyanov, Mathias Lécuyer
In this work, we analyze the optimization behaviour of common private learning optimization algorithms under heavy-tail class imbalanced distribution. We show that, in a stylized m…
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
Mishaal Kazmi, Hadrien Lautraite, Alireza Akbari +5
We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relyin…
DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)
Qiaoyue Tang, Frederick Shpilevskiy, Mathias Lécuyer
The Adam optimizer is a popular choice in contemporary deep learning, due to its strong empirical performance. However we observe that in privacy sensitive scenarios, the tradition…