3 papers
cs.CR2026
Algebraic Attack on Convolutional Neural Networks with Max Pooling
Zirui Chen, Shi Tang, Zhengchao Gao +3
Recovering the weights and biases of deep neural networks (DNNs) via black-box input-output queries, known as parameter extraction attacks, has been extensively studied for ReLU-ba…
cs.CR2026
Algebraic Cryptanalytic Extraction on Hard-Label Neural Networks
Zirui Chen, Shi Tang, Zhengchao Gao +3
Although the state-of-the-art neural network model extraction attack in the hard-label setting by Carlini et al. at EUROCRYPT 2025 has polynomial-time complexity in theory, its dua…
q-bio.NC2024
Universal dimensions of visual representation
Zirui Chen, Michael F. Bonner
Do neural network models of vision learn brain-aligned representations because they share architectural constraints and task objectives with biological vision or because they learn…