检索结果-内蒙古大学图书馆

TruVRF: Toward Triple-Granularity Verification on Machine Unlearning

IEEE Transactions on Information Forensics and Security 2025年 20卷 4844-4859页

作者： Zhou, Chunyi Gao, Yansong Fu, Anmin Chen, Kai Zhang, Zhi Xue, Minhui Dai, Zhiyang Ji, Shouling Zhang, Yuqing Zhejiang University College of Computer Science and Technology Hangzhou310027 China Nanjing University of Science and Technology College of Computer Science and Engineering Nanjing210094 China The University of Western Australia School of Computer Science and Software Engineering PerthWA6009 Australia Chinese Academy of Sciences Beijing100864 China Data61 CSIRO SydneyNSW2122 Australia Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing210094 China University of Chinese Academy of Sciences National Computer Network Intrusion Protection Center Beijing101408 China

The right to be forgotten has incentivized machine unlearning, but a key challenge persists: the lack of reliable methods to verify unlearning conducted by model providers. This gap facilitates dishonest model providers to deceive data contributors. Current approaches often rely on invasive methods like backdoor injection. However, it poses security concerns and is also inapplicable to legacy data—already released data. To tackle this challenge, this work initializes the first non-invasive unlearning verification framework which operates at triple-granularity (class-, volume-, sample-level) to assess the data facticity and volume integrity of machine unlearning. In this paper, we propose a framework, named TruVRF, encompasses three Unlearning-Metrics, each tailored to counter different types of dishonest model providers or servers (Neglecting Server, Lazy Server, Deceiving Server). TruVRF leverages non-invasive model sensitivity to enable multi-granularity verification of unlearning. Specifically, Unlearning-Metric-I checks if the removed class matches the data contributor’s unlearning request, Unlearning-Metric-II measures the amount of unlearned data, and Unlearning-Metric-III validates the correspondence of a specific unlearned sample with the requested deletion. We conducted extensive evaluations of TruVRF efficacy across three datasets, and notably, we also evaluated the effectiveness and computational overhead of TruVRF in real-world applications for the face recognition dataset. Our experimental results demonstrate that TruVRF achieves robust verification performance: Unlearning-Metric-I and -III achieve over 90% verification accuracy on average against dishonest servers, while Unlearning-Metric-II maintains an inference deviation within 4.8% to 8.2%. Additionally, TruVRF demonstrates generalizability across diverse conditions, including varying numbers of unlearned classes and sample volumes. Significantly, TruVRF is applied to two state-of-the-art unlearnin

关键词： data models Servers Sensitivity Solid modeling data privacy Computational modeling Context modeling Adaptation models Analytical models Volume measurement

来源：评论

学校读者我要写书评

暂无评论

FLEKE: Federated Locate-then-Edit Knowledge Editing

arXiv

引用

arXiv 2025年

作者： Zhao, Zongkai Xu, Guozeng Li, Xiuhua Wei, Kaiwen Zhong, Jiang School of Big Data & Software Engineering Chongqing University China College of Computer Science Chongqing University China

Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client scenarios, where decentralized organizations (e.g., hospitals, financial institutions) independently update overlapping knowledge, leading to redundant mediator knowledge vector (MKV) computations and privacy concerns. To address these challenges, we introduce Federated Locate-then-Edit Knowledge Editing (FLEKE), a novel task that enables multiple clients to collaboratively perform LEKE while preserving privacy and reducing computational overhead. To achieve this, we propose FedEdit, a two-stage framework that optimizes MKV selection and reuse. In the first stage, clients locally apply LEKE and upload the computed MKVs. In the second stage, rather than relying solely on server-based MKV sharing, FLEKE allows clients retrieve relevant MKVs based on cosine similarity, enabling knowledge re-edit and minimizing redundant computations. Experimental results on two benchmark datasets demonstrate that FedEdit retains over 96% of the performance of non-federated LEKE while significantly outperforming a FedAvg-based baseline by approximately twofold. Besides, we find that MEMIT performs more consistently than PMET in the FLEKE task with our FedEdit framework. Our code is available at https://***/zongkaiz/FLEKE. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

LLGS: Illuminating Gaussian Splatting via absorptance Modulation

LLGS: Illuminating Gaussian Splatting via absorptance Modula...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Gan, Jianwen Li, Wenxin Zheng, Bo Wang, Chengliang Wu, Yingbo National Elite Institute of Engineering Chongqing University Chongqing China AI Lab Chongqing Changan Automobile Co. Ltd. Chongqing China College of Computer Science Chongqing University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China

ISBN: (纸本)9798350368741

Low-light images are typically characterized by low pixel intensity and color distortion, presenting a significant challenge for accurate 3D reconstruction with 3D Gaussian Splatting (3DGS). Traditional 2D enhancement methods fail to maintain consistent illumination, affecting reconstruction quality. We propose Low-Light Gaussian (LLGS), which can directly leverage low-light images for 3D reconstruction and synthesizing normal-light novel views. LLGS incorporates absorptance to simulate light behavior in low-light conditions, assuming objects maintain normal illumination while reflected light intensity attenuates due to absorptance during rendering. This approach enables the capture of authentic color information in dimly lit scenes. LLGS outperforms current enhancement algorithms and Neural Radiance Fields (NeRF) in image quality and processing efficiency, making it highly effective for low-light 3D scene reconstruction and novel view synthesis. © 2025 IEEE.

关键词： 3D gaussians Low-light image enhancement Novel view synthesis Radiance fields

来源：评论

学校读者我要写书评

暂无评论

Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Li, Shumeng Qi, Lei Yu, Qian Huo, Jing Shi, Yinghuan Gao, Yang Nanjing University State Key Laboratory for Novel Software Technology China Nanjing University National Institute of Healthcare Data Science China School of Computer Science and Engineering China Shandong Women's University School of Data and Computer Science China

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our stitching strategy mitigates the mismatch between natural and 3D medical images. The stitched images are then used for fine-tuning SAM, providing robust initialization of pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. We also develop an extended framework SFR+ with selective fine-tuning and re-training through confidence estimation. Extensive experiments validate that our SFR and SFR+ achieve significant improvements in both moderate annotation and scarce annotation across five datasets. In particular, SFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset. The code is available at https://***/ShumengLI/SFR. © 1982-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Analysis of converting -circuit into -circuit

引用

EPJ Quantum Technology 2025年第1期12卷 1-14页

作者： Luo, Qing-bin Ding, Lang Yang, Guo-wu Li, Xiao-yu College of Intelligent Systems Science and Engineering Hubei Minzu University Enshi China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Big data research Center & School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

A $\mathfrak{C^{*}}$ -circuit, which was proposed in Asiacypt 2022 by Huang and Sun (Advances in cryptology – ASIACRYPT 2022, pp. 614–644, 2022), can directly perform calculations with the existing quantum states, thereby reducing the use of quantum resources in quantum logic synthesis. We theoretically prove how to convert a $\mathfrak{C^{0}}$ -circuit into the corresponding $\mathfrak{C^{*}}$ -circuit through two lemmas and one theorem. The first lemma proves the interchangeability of CNOT gates and NOT gates by using the equivalence of quantum circuits. The second lemma proves that adding CNOT gates to the front of a quantum circuit whose initial states are all $|0\rangle $ s will not change the output states of the circuit. The theorem is used to describe what kind of $\mathfrak{C^{0}}$ -circuit can be transformed into $\mathfrak{C^{*}}$ -circuit, and the correctness of this transformation is proved. Our work will provide a theoretical basis for converting $\mathfrak{C^{0}}$ -circuit to $\mathfrak{C^{*}}$ -circuit. Then applying the theoretical analysis results to the multiplication over $\text{GF}(2^{8})$ , the constructed quantum circuit needs 27 Toffoli gates and 118 CNOT gates, which is 15 fewer Toffoli gates and 43 CNOT gates than the current best result. This shows that the method of constructing quantum circuits by using the conversion of $\mathfrak{C^{0}}$ -circuit to $\mathfrak{C^{*}}$ -circuit is very efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Yujun Chen, Yanqu Wang, Jiakai Hu, Jin Tao, Renshuai Liu, Xianglong State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (纸本)9798350368741

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression. © 2025 IEEE.

关键词： Automatic speech recognition natural noise pattern phoneme-level targeted universal adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Class-wise Adaptive Logits Distillation with Meta-Learning

Class-wise Adaptive Logits Distillation with Meta-Learning

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiao Huang Wu Chen Wei Zhou College of Computer and Information Science College of Software Southwest University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Knowledge distillation has become a crucial technique for transferring intricate knowledge from a teacher model to a smaller student model. While logit-based knowledge distillation has shown promise, existing methods often overlook the efficient distillation of logits. In this paper, we introduce a novel approach called Class-wise Adaptive Logits Distillation (CALD) based on meta-learning. Our method leverages a meta-network to generate class-adaptive weights, delivering both explicit and implicit knowledge adaptively. By training the meta-network to assign higher weights to specific classes crucial for the student model’s learning from the teacher model, our approach enhances the knowledge transfer process. Experimental results on CIFAR-100 and ImageNet datasets demonstrate that CALD surpasses state-of-the-art knowledge distillation methods, achieving enhanced accuracy and efficiency in transferring knowledge from teacher to student models.

关键词： Metalearning Training Adaptation models Accuracy Signal processing Acoustics Speech processing Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Parallel Key-Insulated Multi-Receiver Signcryption Scheme for IoV

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5123-5137页

作者： Hou, Yingzhe Cao, Yue Xiong, Hu He, Debiao Chi, Chi-Hung Lam, Kwok-Yan Wuhan University School of Cyber Science and Engineering Wuhan430000 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Nanyang Technological University College of Computing and Data Science 639798 Singapore

The rapid growth of electric vehicle and autonomous vehicle populations has led to explosive expansion of IoV data being transmitted in the wireless communication infrastructure. Advances in IoV technologies also resulted in more complex and dynamic communication protocols/patterns, which are hard for the underlying wireless network to satisfy. Besides, security considerations of IoV communications require that key management must be stringently prohibit global failure mode of key management, meaning that, if a single IoV node compromises its private key, it will not lead to total security failure of the entire IoV network. To address these issues, in this paper, we propose a heterogeneous parallel key-insulated multi-receiver signcryption scheme for IoV (HPKI-MRSC). Firstly, the proposed scheme can realize one-to-many heterogeneous transmission, in which RSUs are deployed on certificateless cryptography (CLC) system, while vehicles are allocated in identity-based cryptography (IBC) system. In this manner, we observe that message transmission efficiency is improved greatly. Secondly, the parallel key-insulated mechanism can employ two helper keys to update private key periodically, and then solve key disclosure problem. Finally, when the number of receiver n is greater than or equal to 3, the proposed scheme has a lower signcryption overhead than other comparative schemes, and thus it is more suitable for IoV. © 2005-2012 IEEE.

关键词： Heterogeneous Internet of Vehicle (IoV) Parallel Key-Insulated Signcryption

来源：评论

学校读者我要写书评

暂无评论

MPNAS: Multimodal Sentiment Analysis Pruning via Neural Architecture Search

MPNAS: Multimodal Sentiment Analysis Pruning via Neural Arch...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Binyan Zhang Ao Ren Zihao Zhang Moming Duan Duo Liu Yujuan Tan Kan Zhong College of Computer Science Chongqing University Chongqing China School of Big Data Software & Engineering Chongqing University Chongqing China Institute of Data Science National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid development of social media, sentiment analysis from multimodal posts has garnered significant attention in recent years. However, the substantial size of these models impedes their deployment on resource-constrained embedded devices. Although pruning has been extensively studied to reduce the size of unimodal models, specific challenges remain for Multimodal Sentiment Analysis (MSA) models. First, existing techniques prune fixed original models into sparse models, while our findings indicate that different model architectures of identical size yield varying performance outcomes. Second, prior studies fail to explore the unique characteristics of MSA models, resulting in suboptimal pruning performance. To address these challenges, we propose MPNAS, a unified pruning framework via Neural Architecture Search (NAS) for MSA models. Specifically, we formulate pruning as a NAS problem and analyze MSA model characteristics to guide the subnet search. We conduct an initial coarse-grained NAS on the original model, expanding the search space slightly to identify suitable subnets that enhance pruning rates and accuracy. Subsequently, we refine coarse-grained subnets in a fine-grained NAS stage, where MSA model characteristics guide the search process. Extensive experiments on three representative datasets demonstrate the superiority of our approach over existing methods.

关键词： Performance evaluation Analytical models Sentiment analysis Accuracy Social networking (online) Signal processing Search problems Acoustics Neural architecture search Speech processing

来源：评论

学校读者我要写书评

暂无评论

HyperDiff: Masked Diffusion Model with High-efficient Transformer for Hyperspectral Image Cross-Scene Classification

HyperDiff: Masked Diffusion Model with High-efficient Transf...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Pei Wang, Dong Wu, Chanyue Yang, Jing Kang, Lei Bai, Zongwen Li, Ying Shen, Qiang School of Computer Science Northwestern Polytechnical University Xi'an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan'an University Yan'an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd. Qingdao China Department of Computer Science Aberystwyth University Aberystwyth United Kingdom

ISBN: (纸本)9798350368741

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques. © 2025 IEEE.

关键词： Cross-scene classification Diffusion model Hyperspectral image Transformer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：