Shiming Ge

Distilling Deep Neural Networks for Robust Classification with Soft Decision Trees

2018

Recent deep neural networks have achieved impressive performance in image classification. However, these networks are sensitive to the attack of adversarial examples, leading to a sharp drop in accuracy. To address this issue, this paper …

Defending Against Adversarial Examples via Soft Decision Trees Embedding

2019

Convolutional neural networks (CNNs) have shown vulnerable to adversarial examples which contain imperceptible perturbations. In this paper, we propose an approach to defend against adversarial examples with soft decision trees embedding. Firstly, we extract the …

Trustable Co-Label Learning From Multiple Noisy Annotators

2021 · IEEE Transactions on Multimedia

Supervised deep learning depends on massive accurately annotated examples, which is usually impractical in many real-world scenarios. A typical alternative is learning from multiple noisy annotators. Numerous earlier works assume that all labels are noisy, …

Model Conversion via Differentially Private Data-Free Distillation

2023 · arXiv (Cornell University)

While massive valuable deep models trained on large-scale data have been released to facilitate the artificial intelligence community, they may encounter attacks in deployment which leads to privacy leakage of training data. In this work, …

Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation

2024 · arXiv (Cornell University)

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective …