2 papers
cs.LG2026
Let the Neurons Die: Exploiting ReLU-Induced Model Degradation
Kexin Li, Wenjun Qiu, Joshua Abraham +2
Rectified linear unit (ReLU) networks can suffer from dying neurons, where units with persistently negative pre-activations produce zero outputs, blocking gradients through their a…
cs.LG2024
LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation
Kexin Li, Aastha Mehta, David Lie
To protect privacy in regulated domains such as healthcare and finance, model owners may allow only remote API access while keeping both the training data and model parameters priv…