检索结果-内蒙古大学图书馆

MISA: UNVEILING THE VULNERABILITIES IN SPLIT FEDERATED LEARNING

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Li, Minghui Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users' devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of robustness. In this paper, we present a novel poisoning attack known as MISA. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention. Copyright © 2023, The Authors. All rights reserved.

关键词：

OCDB: REVISITING CAUSAL DISCOVERY WITH A COMPREHENSIVE BENCHMARK AND EVALUATION FRAMEWORK

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Wei Huang, Hong Zhang, Guowen Shi, Ruize Yin, Kehan Lin, Yuanyuan Liu, Bang Huazhong University of Science and Technology China DIRO Université de Montréal & Mila Canada CIFAR AI Chair Canada The National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Large language models (LLMs) have excelled in various natural language processing tasks, but challenges in interpretability and trustworthiness persist, limiting their use in high-stakes fields. Causal discovery offers a promising approach to improve transparency and reliability. However, current evaluations are often one-sided and lack assessments focused on interpretability performance. Additionally, these evaluations rely on synthetic data and lack comprehensive assessments of real-world datasets. These lead to promising methods potentially being overlooked. To address these issues, we propose a flexible evaluation framework with metrics for evaluating differences in causal structures and causal effects, which are crucial attributes that help improve the interpretability of LLMs. We introduce the Open Causal Discovery Benchmark (OCDB), based on real data, to promote fair comparisons and drive optimization of algorithms. Additionally, our new metrics account for undirected edges, enabling fair comparisons between Directed Acyclic Graphs (DAGs) and Completed Partially Directed Acyclic Graphs (CPDAGs). Experimental results show significant shortcomings in existing algorithms' generalization capabilities on real data, highlighting the potential for performance improvement and the importance of our framework in advancing causal discovery techniques. Copyright © 2024, The Authors. All rights reserved.

关键词： Directed graphs

Medium-Term Water Consumption Forecasting Based on Deep Neural Networks

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Gamboa, A. Gil Paneque, Pilar Trull, O. Troncoso, Alicia Data Science and Big Data Lab Pablo de Olavide University SevilleES-41013 Spain Department of Geography History and Philosophy Pablo de Olavide University SevilleES-41013 Spain Department of Applied Statistics and Operational Research and Quality Universitat Politècnica de València ValenciaES-46022 Spain

Water consumption forecasting is an essential tool for water management, as it allows for efficient planning and allocation of water resources, an undervalued but indispensable resource for all living beings. With the increasing demand for accurate and timely water forecasting, traditional forecasting methods are proving to be insufficient. Deep learning techniques, which have shown remarkable performance in a wide range of applications, offer a promising approach to address the challenges of water consumption forecasting. In this work, the use of deep learning models for medium-term water consumption forecasting of residential areas is explored. A deep feed-forward neural network is developed to predict water consumption of a company’s customers for the next quarter. First, customers are grouped according to their consumption as these customers include both household consumers and special consumers such as public swimming pools, sports halls or small industries. Then, a deep feed-forward neural network is designed for household customers by obtaining the optimal values for those hyperparameters that have a great influence on the network performance. Results are reported using a real-world dataset composed of the water consumption from 1999 to 2015 on a quarterly basis, corresponding to 3262 clients of a water supply company. Finally, the proposed algorithm is evaluated by comparing it with other reference algorithms including an LSTM network. © 2023, The Authors. All rights reserved.

关键词： Water management

Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wan, Wei Hu, Shengshan Lu, Jianrong Yu Zhang, Leo Jin, Hai He, Yuanyuan School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab School of Information Technology Deakin University Australia

Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients’ data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. Although the problem has gained significant attention, existing defenses have several flaws: the server irrationally chooses malicious clients for aggregation even after they have been detected in previous rounds;the defenses perform ineffectively against sybil attacks or in the heterogeneous data setting. To overcome these issues, we propose MAB-RFL, a new method for robust aggregation in FL. By modelling the client selection as an extended multi-armed bandit (MAB) problem, we propose an adaptive client selection strategy to choose honest clients that are more likely to contribute high-quality updates. We then propose two approaches to identify malicious updates from sybil and non-sybil attacks, based on which rewards for each client selection decision can be accurately evaluated to discourage malicious behaviors. MAB-RFL achieves a satisfying balance between exploration and exploitation on the potential benign clients. Extensive experimental results show that MAB-RFL outperforms existing defenses in three attack scenarios under different percentages of attackers. Copyright © 2022, The Authors. All rights reserved.

关键词： data privacy

Accelerating parallel sampling of diffusion models 24

学校读者我要写书评

暂无评论

Accelerating parallel sampling of diffusion models

Proceedings of the 41st International Conference on Machine Learning

作者： Zhiwei Tang Jiasheng Tang Hao Luo Fan Wang Tsung-Hui Chang School of Science and Engineering The Chinese University of Hong Kong Shenzhen China DAMO Academy Alibaba Group and Hupan Lab Zhejiang Province DAMO Academy Alibaba Group School of Science and Engineering The Chinese University of Hong Kong Shenzhen China and Shenzhen Research Institute of Big Data Shenzhen China

Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling process. In this work, we propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Specifically, we reformulate the sampling process as solving a system of triangular nonlinear equations through fixed-point iteration. With this innovative formulation, we explore several systematic techniques to further reduce the iteration steps required by the solving process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm that can leverage extra computational and memory resources to increase the sampling speed. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4∼14 times. Notably, when applying ParaTAA with 100 steps DDIM for Stable Diffusion, a widely-used text-to-image diffusion model, it can produce the same images as the sequential sampling in only 7 inference steps. The code is available at https://***/TZW1998/ParaTAA-Diffusion.

关键词：

A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Ziqiang Sun, Hong Xia, Pengfei Xia, Beihao Rui, Xue Zhang, Wei Guo, Qinglang Fu, Zhangjie Li, Bin Nanjing University of Information Science and Technology China Big Data and Decision Lab University of Science and Technology of China China Huawei Technologies Co. Ltd. China Huazhong University of Science and Technology China China Academic of Electronics and Information Technology China

Poisoning efficiency is crucial in poisoning-based backdoor attacks, as attackers aim to minimize the number of poisoning samples while maximizing attack efficacy. Recent studies have sought to enhance poisoning efficiency by selecting effective samples. However, these studies typically rely on a proxy backdoor injection task to identify an efficient set of poisoning samples. This proxy attack-based approach can lead to performance degradation if the proxy attack settings differ from those of the actual victims, due to the shortcut nature of backdoor learning. Furthermore, proxy attack-based methods are extremely time-consuming, as they require numerous complete backdoor injection processes for sample selection. To address these concerns, we present a Proxy attack-Free Strategy (PFS) designed to identify efficient poisoning samples based on the similarity between clean samples and their corresponding poisoning samples, as well as the diversity of the poisoning set. The proposed PFS is motivated by the observation that selecting samples with high similarity between clean and corresponding poisoning samples results in significantly higher attack success rates compared to using samples with low similarity. Additionally, we provide theoretical foundations to explain the proposed PFS. We comprehensively evaluate the proposed strategy across various datasets, triggers, poisoning rates, architectures, and training hyperparameters. Our experimental results demonstrate that PFS enhances backdoor attack efficiency while also offering a remarkable speed advantage over previous proxy attack-based selection methodologies. © 2023, CC BY.

关键词：

Rethink Video Retrieval Representation for Video Captioning

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Tian, Mingkai Li, Guorong Qi, Yuankai Wang, Shuhui Sheng, Quan Z. Huang, Qingming School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China School of Computing Macquarie University Australia Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy of Sciences China

Video captioning, a challenging task targeting the automatic generation of accurate and comprehensive descriptions based on video content, has witnessed substantial success recently driven by bridging video representations and textual semantics. Inspired by the nature of the video retrieval task, which learns visual features strongly related to text queries, we propose to take advantage of visual representation learning from the video retrieval framework to tackle video captioning tasks. However, a simple direct application of video retrieval models performs poorly due to the weak ability to capture sufficient video details and temporal information required for video captioning. To increase the attention on details, we propose a learnable token shift module, which flexibly captures subtle movements in local regions across the temporal sequence. Furthermore, we devise a Refineformer, which learns to integrate local video tokens strongly related to desired captions via a cross-attention mechanism. Extensive experiments on MSVD, MSR-VTT and VATEX demonstrate the favorable performance of our method. © 2024, The Authors. All rights reserved.

关键词： Semantics

Which Pixel to Annotate: a label-Efficient Nuclei Segmentation Framework

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lou, Wei Li, Haofeng Li, Guanbin Han, Xiaoguang Wan, Xiang Shenzhen Research Institute of Big Data Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong at Shenzhen Shenzhen518172 China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Pazhou Lab Guangzhou510330 China

Recently deep neural networks, which require a large amount of annotated samples, have been widely applied in nuclei instance segmentation of H&E stained pathology images. However, it is inefficient and unnecessary to label all pixels for a dataset of nuclei images which usually contain similar and redundant patterns. Although unsupervised and semi-supervised learning methods have been studied for nuclei segmentation, very few works have delved into the selective labeling of samples to reduce the workload of annotation. Thus, in this paper, we propose a novel full nuclei segmentation framework that chooses only a few image patches to be annotated, augments the training set from the selected samples, and achieves nuclei segmentation in a semi-supervised manner. In the proposed framework, we first develop a novel consistency-based patch selection method to determine which image patches are the most beneficial to the training. Then we introduce a conditional single-image GAN with a component-wise discriminator, to synthesize more training samples. Lastly, our proposed framework trains an existing segmentation model with the above augmented samples. The experimental results show that our proposed method could obtain the same-level performance as a fully-supervised baseline by annotating less than 5% pixels on some benchmarks. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Hao Peng, Zhiyuan Li, Xu Shao, Mingjie Wu, Xixin Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Stanley Ho Big Data Decision Analytics Research Centre The Chinese University of Hong Kong Hong Kong

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation1 © 2024, CC BY.

关键词： Query languages