Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
A Game-theoretic Framework for Privacy-preserving Federated Learning
ACM Transactions on Intelligent Systems and Technology (TIST), Volume 15, Issue 3Article No.: 52, Pages 1–35https://doi.org/10.1145/3656049In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of privacy leakage cannot be ignored in the presence of semi-honest adversaries. Existing research has focused either on designing protection ...
- research-articleMay 2024
A Meta-Learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
ACM Transactions on Intelligent Systems and Technology (TIST), Volume 15, Issue 3Article No.: 55, Pages 1–36https://doi.org/10.1145/3652612Trustworthy federated learning typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency reduction while protecting data privacy. Therefore, protection mechanisms and ...
- ArticleMay 2024
SecureBoost: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree
Advances in Knowledge Discovery and Data MiningPages 237–249https://doi.org/10.1007/978-981-97-2259-4_18AbstractGradient boosting decision tree (GBDT) is an ensemble machine learning algorithm that is widely used in industry. Due to the problem of data isolation and the requirement of privacy, many works try to use vertical federated learning to train ...
- research-articleMarch 2024
FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 46, Issue 9Pages 5905–5920https://doi.org/10.1109/TPAMI.2024.3375287This paper proposes a general <italic>spectral analysis</italic> framework that thwarts a security risk in federated Learning caused by <italic>groups of malicious Byzantine attackers</italic> or <italic>colluders</italic>, who conspire to upload vicious ...
-
- research-articleDecember 2023
Reconstructing Close Human Interactions from Multiple Views
ACM Transactions on Graphics (TOG), Volume 42, Issue 6Article No.: 273, Pages 1–14https://doi.org/10.1145/3618336This paper addresses the challenging task of reconstructing the poses of multiple individuals engaged in close interactions, captured by multiple calibrated cameras. The difficulty arises from the noisy or false 2D keypoint detections due to inter-person ...
- research-articleNovember 2023
Trading Off Privacy, Utility, and Efficiency in Federated Learning
ACM Transactions on Intelligent Systems and Technology (TIST), Volume 14, Issue 6Article No.: 98, Pages 1–32https://doi.org/10.1145/3595185Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in ...
- ArticleDecember 2023
MaskDiffuse: Text-Guided Face Mask Removal Based on Diffusion Models
AbstractAs masked face images can significantly degrade the performance of face-related tasks, face mask removal remains an important and challenging task. In this paper, we propose a novel learning framework, called MaskDiffuse, to remove face masks ...
- ArticleDecember 2023
Learning Adapters for Text-Guided Portrait Stylization with Pretrained Diffusion Models
AbstractThis paper presents a framework for text-guided face portrait stylization using a pre-trained large-scale diffusion model. To balance style transformation and content preservation, we introduce an adapter that modifies specific components of the ...
- research-articleAugust 2023
FedPass: privacy-preserving vertical federated deep learning with adaptive obfuscation
IJCAI '23: Proceedings of the Thirty-Second International Joint Conference on Artificial IntelligenceArticle No.: 418, Pages 3759–3767https://doi.org/10.24963/ijcai.2023/418Vertical federated learning (VFL) allows an active party with labeled feature to leverage auxiliary features from the passive parties to improve model performance. Concerns about the private feature and label leakage in both the training and inference ...
- ArticleMay 2023
Achieving Provable Byzantine Fault-tolerance in a Semi-honest Federated Learning Setting
Advances in Knowledge Discovery and Data MiningPages 415–427https://doi.org/10.1007/978-3-031-33377-4_32AbstractFederated learning (FL) is a suite of technology that allows multiple distributed participants to collaboratively build a global machine learning model without disclosing private datasets to each other. We consider an FL setting in which there may ...
- research-articleApril 2023
FedIPR: Ownership Verification for Federated Deep Neural Network Models
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 45, Issue 4Pages 4521–4536https://doi.org/10.1109/TPAMI.2022.3195956Federated learning models are collaboratively developed upon valuable training data owned by multiple parties. During the development and deployment of federated models, they are exposed to risks including illegal copying, re-distribution, misuse and/or ...
- research-articleNovember 2022
No Free Lunch Theorem for Security and Utility in Federated Learning
ACM Transactions on Intelligent Systems and Technology (TIST), Volume 14, Issue 1Article No.: 1, Pages 1–35https://doi.org/10.1145/3563219In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. On one hand, private and sensitive training data must be kept secure as ...
- research-articleOctober 2022
DeepIPR: Deep Neural Network Ownership Verification With Passports
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 44, Issue 10_Part_1Pages 6122–6139https://doi.org/10.1109/TPAMI.2021.3088846With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed, or abused ...
- research-articleSeptember 2022
Intrinsic Performance Influence-based Participant Contribution Estimation for Horizontal Federated Learning
ACM Transactions on Intelligent Systems and Technology (TIST), Volume 13, Issue 6Article No.: 88, Pages 1–24https://doi.org/10.1145/3523059The rapid development of modern artificial intelligence technique is mainly attributed to sufficient and high-quality data. However, in the data collection, personal privacy is at risk of being leaked. This issue can be addressed by federated learning, ...
- research-articleFebruary 2022
Protect, show, attend and tell: Empowering image captioning models with ownership protection
Highlights- We propose a key-based strategy that provides reliable, preventive and timely IP protection for image captioning task.
By and large, existing Intellectual Property (IP) protection on deep neural networks typically i) focus on image classification task only, and ii) follow a standard digital watermarking framework that was conventionally used to protect ...
- research-articleOctober 2021
L2RS: A Learning-to-Rescore Mechanism for Hybrid Speech Recognition
MM '21: Proceedings of the 29th ACM International Conference on MultimediaPages 1157–1166https://doi.org/10.1145/3474085.3481542This paper aims to advance the performance of industrial ASR systems by exploring a more effective method for N-best rescoring, a critical step that greatly affects the final recognition accuracy. Existing rescoring approaches suffer the following ...
- ArticleSeptember 2021
ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment
- Chun Chet Ng,
- Akmalul Khairi Bin Nazaruddin,
- Yeong Khang Lee,
- Xinyu Wang,
- Yuliang Liu,
- Chee Seng Chan,
- Lianwen Jin,
- Yipeng Sun,
- Lixin Fan
Document Analysis and Recognition – ICDAR 2021Pages 663–677https://doi.org/10.1007/978-3-030-86337-1_44AbstractWith hundreds of thousands of electronic chip components are being manufactured every day, chip manufacturers have seen an increasing demand in seeking a more efficient and effective way of inspecting the quality of printed texts on chip ...
- research-articleAugust 2021
Fast black-box quantum state preparation based on linear combination of unitaries
- Shengbin Wang,
- Zhimin Wang,
- Guolong Cui,
- Shangshang Shi,
- Ruimin Shang,
- Lixin Fan,
- Wendong Li,
- Zhiqiang Wei,
- Yongjian Gu
AbstractBlack-box quantum state preparation is a fundamental primitive in quantum algorithms. Starting from Grover, a series of techniques have been devised to reduce the complexity. In this work, we propose to perform black-box state preparation using ...