Search Results for author: Ziqi Yang

Found 10 papers, 2 papers with code

Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment

1 code implementation22 Feb 2019 Ziqi Yang, Ee-Chien Chang, Zhenkai Liang

In this work, we investigate the model inversion problem in the adversarial settings, where the adversary aims at inferring information about the target model's training data and test data from the model's prediction values.

Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarking

no code implementations14 Jun 2019 Ziqi Yang, Hung Dang, Ee-Chien Chang

In this paper, we show that distillation, a widely used transformation technique, is a quite effective attack to remove watermark embedded by existing algorithms.

Statistical Outlier Identification in Multi-robot Visual SLAM using Expectation Maximization

no code implementations7 Feb 2020 Arman Karimian, Ziqi Yang, Roberto Tron

This paper introduces a novel and distributed method for detecting inter-map loop closure outliers in simultaneous localization and mapping (SLAM).

Outlier Detection Simultaneous Localization and Mapping

Defending Model Inversion and Membership Inference Attacks via Prediction Purification

no code implementations8 May 2020 Ziqi Yang, Bin Shao, Bohan Xuan, Ee-Chien Chang, Fan Zhang

Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence scores predicted by the target classifier.

Inference Attack Membership Inference Attack

Purifier: Defending Data Inference Attacks via Transforming Confidence Scores

no code implementations1 Dec 2022 Ziqi Yang, Lijin Wang, Da Yang, Jie Wan, Ziming Zhao, Ee-Chien Chang, Fan Zhang, Kui Ren

Besides, our further experiments show that PURIFIER is also effective in defending adversarial model inversion attacks and attribute inference attacks.

Attribute Inference Attack +1

Asymmetric Co-Training with Explainable Cell Graph Ensembling for Histopathological Image Classification

no code implementations24 Aug 2023 Ziqi Yang, Zhongyu Li, Chen Liu, Xiangde Luo, Xingguang Wang, Dou Xu, CHAOQUN LI, Xiaoying Qin, Meng Yang, Long Jin

To make full use of pixel-level and cell-level features dynamically, we propose an asymmetric co-training framework combining a deep graph convolutional network and a convolutional neural network for multi-class histopathological image classification.

Classification Histopathological Image Classification +1

Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model

no code implementations17 Sep 2023 Ziqi Yang, Xuhai Xu, Bingsheng Yao, Shao Zhang, Ethan Rogers, Stephen Intille, Nawar Shara, Guodong Gordon Gao, Dakuo Wang

(2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system.

Language Modelling Large Language Model

Towards Fair Graph Federated Learning via Incentive Mechanisms

1 code implementation20 Dec 2023 Chenglu Pan, Jiarong Xu, Yue Yu, Ziqi Yang, Qingbiao Wu, Chunping Wang, Lei Chen, Yang Yang

Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.

Fairness Federated Learning +1

Rotational Outlier Identification in Pose Graphs Using Dual Decomposition

no code implementations ECCV 2020 Arman Karimian, Ziqi Yang, Roberto Tron

In the last few years, there has been an increasing trend to consider Structure from Motion (SfM, in computer vision) and Simultaneous Localization and Mapping (SLAM, in robotics) problems from the point of view of pose averaging (also known as global SfM, in computer vision) or Pose Graph Optimization (PGO, in robotics), where the motion of the camera is reconstructed by considering only relative rigid body transformations instead of including also 3-D points (as done in a full Bundle Adjustment).

Outlier Detection Simultaneous Localization and Mapping

Cannot find the paper you are looking for? You can Submit a new open access paper.