activity
20182022
most citedFast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers

60 citations · 201 across the 17 of their papers we have counts for

collaborators

26 papers

cs.IT2022

Secrecy Rate Maximization of RIS-assisted SWIPT Systems: A Two-Timescale Beamforming Design Approach

Ming-Min Zhao, Kaidi Xu, Yunlong Cai +2

Reconfigurable intelligent surfaces (RISs) achieve high passive beamforming gains for signal enhancement or interference nulling by dynamically adjusting their reflection coefficie…

cs.LG2022

Audit and Improve Robustness of Private Neural Networks on Encrypted Data

Jiaqi Xue, Lei Xu, Lin Chen +3

Performing neural network inference on encrypted data without decryption is one popular method to enable privacy-preserving neural networks (PNet) as a service. Compared with regul…

cs.NE20228 cited

Toward Robust Spiking Neural Network Against Adversarial Perturbation

Ling Liang, Kaidi Xu, Xing Hu +2

As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical applications, the security concerns in SNNs attract more attention. Currently, researc…

cs.CV202113 cited

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

Husheng Han, Kaidi Xu, Xing Hu +6

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or defor…

cs.LG20211 cited

Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression

Sheng Lin, Wei Jiang, Wei Wang +4

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.…

cs.LG2021

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification

Shiqi Wang, Huan Zhang, Kaidi Xu +4

Bound propagation based incomplete neural network verifiers such as CROWN are very efficient and can significantly accelerate branch-and-bound (BaB) based complete verification of…