14 citations · 43 across the 14 of their papers we have counts for
14 papers
Towards Tracing Code Provenance with Code Watermarking
Wei Li, Borui Yang, Yujie Sun +5
Recent advances in large language models have raised wide concern in generating abundant plausible source code without scrutiny, and thus tracing the provenance of code emerges as…
Crossword: A Semantic Approach to Data Compression via Masking
Mingxiao Li, Rui Jin, Liyao Xiang +2
The traditional methods for data compression are typically based on the symbol-level statistics, with the information source modeled as a long sequence of i.i.d. random variables o…
Permutation Equivariance of Transformers and Its Applications
Hengyuan Xu, Liyao Xiang, Hangyu Ye +3
Revolutionizing the field of deep learning, Transformer-based models have achieved remarkable performance in many tasks. Recent research has recognized these models are robust to s…
Decentralized Multi-AGV Task Allocation based on Multi-Agent Reinforcement Learning with Information Potential Field Rewards
Mengyuan Li, Bin Guo, Jiangshan Zhang +5
Automated Guided Vehicles (AGVs) have been widely used for material handling in flexible shop floors. Each product requires various raw materials to complete the assembly in produc…
Privacy Threats Analysis to Secure Federated Learning
Yuchen Li, Yifan Bao, Liyao Xiang +4
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never le…
Improved Matrix Gaussian Mechanism for Differential Privacy
Jungang Yang, Liyao Xiang, Weiting Li +2
The wide deployment of machine learning in recent years gives rise to a great demand for large-scale and high-dimensional data, for which the privacy raises serious concern. Differ…
Privacy-Preserving Federated Learning on Partitioned Attributes
Shuang Zhang, Liyao Xiang, Xi Yu +4
Real-world data is usually segmented by attributes and distributed across different parties. Federated learning empowers collaborative training without exposing local data or model…
High-Order Relation Construction and Mining for Graph Matching
Hui Xu, Liyao Xiang, Youmin Le +4
Graph matching pairs corresponding nodes across two or more graphs. The problem is difficult as it is hard to capture the structural similarity across graphs, especially on large g…
Certified Distributional Robustness on Smoothed Classifiers
Jungang Yang, Liyao Xiang, Ruidong Chen +3
The robustness of deep neural networks (DNNs) against adversarial example attacks has raised wide attention. For smoothed classifiers, we propose the worst-case adversarial loss ov…
Achieving Adversarial Robustness via Sparsity
Shufan Wang, Ningyi Liao, Liyao Xiang +2
Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanis…
Rotation-Equivariant Neural Networks for Privacy Protection
Hao Zhang, Yiting Chen, Haotian Ma +5
In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant…
Deep Quaternion Features for Privacy Protection
Hao Zhang, Yiting Chen, Liyao Xiang +3
We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input informa…
Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
Shuang Zhang, Liyao Xiang, Congcong Li +4
Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market. As deep learning tasks are mostly computation-…
Interpretable Complex-Valued Neural Networks for Privacy Protection
Liyao Xiang, Haotian Ma, Hao Zhang +3
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such ad…