Xuan Liu

Model-Based Minimum Privacy Disclosure Recommendation for Authorization Policies

2016

This paper presents a privacy disclosure recommendation approach based on a privacy cost model. The approach involves selecting appropriate credentials or attributes from users, and automatically building a new credential to fulfill service's authorization policies. …

Improving the Interpretability of Deep Neural Networks with Knowledge Distillation

2018

Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not enough to satisfy the needs of practical …

Learning to Transfer Under Unknown Noisy Environments: An Universal Weakly-Supervised Domain Adaptation Method

2021

Weakly-supervised domain adaptation has been introduced to address the source domain with label noise or/and feature noise. However, the existing weakly-supervised domain adaptation methods only work under ideal assumptions, which assume either the annotated data …

Research on Intelligent Desk Design

2021

To explore the innovative design of intelligent desk. With researching and analyzing the current situation of intelligent desk, this paper figures out problems and design trends of intelligent desk, and formulates the feasibility of realizing …

Research on Mono‐Pulse Beam Angle Tracking Algorithm of Phased Array Antenna Based on CKF

2022 · Wireless Communications and Mobile Computing

Phased array antenna beam tracking and communication system based on mono‐pulse system is an alternative satellite‐to‐earth communication technology solution for future planetary spacecraft, which meets the mission requirements of agile scanning, multimode, wide field of …

Multi-Class Hypersphere Anomaly Detection Based on Edge Outlier Exposure Set and Margin

2024 · Mathematics

Currently, the decision boundary of the multi-class anomaly detection algorithm based on deep learning does not sufficiently capture the positive class region, posing a risk of abnormal sample features falling into the domain of normal …

Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leaked gradients. However, can gradient perturbation protection mechanisms truly …

DAPrompt: Dual Alignment Prompt of Structure and Semantics for Few-shot Graph Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Few-shot graph learning remains a fundamental yet challenging problem, especially under heterophilic graph settings where connected nodes are likely to belong to different classes. In such scenarios, two key challenges arise: (1) unreliable or noisy …

DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications

2018

Wei He, Kai Liu, Jing Liu, Yajuan Lyu, Shiqi Zhao, Xinyan Xiao, Yuan Liu, Yizhong Wang, Hua Wu, Qiaoqiao She, Xuan Liu, Tian Wu, Haifeng Wang. Proceedings of the Workshop on Machine Reading for Question …