检索结果-内蒙古大学图书馆

Fairness is essential for robustness:fair adversarial training by identifying and augmenting hard examples

Frontiers of Computer Science 2025年第3期19卷 1-13页

作者： Ningping MOU Xinli YUE Lingchen ZHAO Qian WANG Key Laboratory of Aerospace Information Security and Trusted Computing(Ministry of Education) School of Cyber Science and EngineeringWuhan UniversityWuhan 430072China

Adversarial training has been widely considered the most effective defense against adversarial ***,recent studies have demonstrated that a large discrepancy exists in the class-wise robustness of adversarial training,leading to two potential issues:firstly,the overall robustness of a model is compromised due to the weakest class;and secondly,ethical concerns arising from unequal protection and biases,where certain societal demographic groups receive less robustness in defense *** these issues,solutions to address the discrepancy remain largely *** this paper,we advance beyond existing methods that focus on class-level *** investigation reveals that hard examples,identified by higher cross-entropy values,can provide more fine-grained information about the ***,we find that enhancing the diversity of hard examples can effectively reduce the robustness gap between *** by these observations,we propose Fair Adversarial Training(FairAT)to mitigate the discrepancy of class-wise *** experiments on various benchmark datasets and adversarial attacks demonstrate that FairAT outperforms state-of-the-art methods in terms of both overall robustness and *** a WRN-28-10 model trained on CIFAR10,FairAT improves the average and worst-class robustness by 2.13%and 4.50%,respectively.

关键词： robust fairness adversarial training hard example data augmentation

来源：评论

学校读者我要写书评

暂无评论

Committed-programming reductions: formalizations,implications and relations

引用

Science China(Information Sciences) 2024年第10期67卷 151-171页

作者： Jiang ZHANG Yu YU Dengguo FENG Shuqin FAN Zhenfeng ZHANG State Key Laboratory of Cryptology Department of Computer Science and Engineering Shanghai Jiao Tong University Trusted Computing and Information Assurance Laboratory Institute of SoftwareChinese Academy of Sciences

In this work, we introduce a class of black-box(BB) reductions called committed-programming reduction(CPRed) in the random oracle model(ROM) and obtain the following interesting results:(1) we demonstrate that some well-known schemes, including the full-domain hash(FDH) signature(Eurocrypt1996) and the Boneh-Franklin identity-based encryption(IBE) scheme(Crypto 2001), are provably secure under CPReds;(2) we prove that a CPRed associated with an instance-extraction algorithm implies a reduction in the quantum ROM(QROM). This unifies several recent results, including the security of the Gentry-Peikert-Vaikuntanathan IBE scheme by Zhandry(Crypto 2012) and the key encapsulation mechanism(KEM) variants using the Fujisaki-Okamoto transform by Jiang et al.(Crypto 2018) in the ***, we show that CPReds are incomparable to non-programming reductions(NPReds) and randomly-programming reductions(RPReds) formalized by Fischlin et al.(Asiacrypt 2010).

关键词： provable security random oracle model quantum random oracle model black-box reduction/separation programmability

来源：评论

学校读者我要写书评

暂无评论

HGNN-ETC: Higher-Order Graph Neural Network Based on Chronological Relationships for Encrypted Traffic Classification

引用

Computers, Materials & Continua 2024年第11期81卷 2643-2664页

作者： Rongwei Yu Xiya Guo Peihao Zhang Kaijuan Zhang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan430072China

Encrypted traffic plays a crucial role in safeguarding network security and user ***,encrypting malicious traffic can lead to numerous security issues,making the effective classification of encrypted traffic *** methods for detecting encrypted traffic face two significant ***,relying solely on the original byte information for classification fails to leverage the rich temporal relationships within network ***,machine learning and convolutional neural network methods lack sufficient network expression capabilities,hindering the full exploration of traffic’s potential *** address these limitations,this study introduces a traffic classification method that utilizes time relationships and a higher-order graph neural network,termed *** approach fully exploits the original byte information and chronological relationships of traffic packets,transforming traffic data into a graph structure to provide the model with more comprehensive context ***-ETC employs an innovative k-dimensional graph neural network to effectively capture the multi-scale structural features of traffic graphs,enabling more accurate *** select the ISCXVPN and the USTC-TK2016 dataset for our *** results show that compared with other state-of-the-art methods,our method can obtain a better classification effect on different datasets,and the accuracy rate is about 97.00%.In addition,by analyzing the impact of varying input specifications on classification performance,we determine the optimal network data truncation strategy and confirm the model’s excellent generalization ability on different datasets.

关键词： Encrypted network traffic graph neural network traffic classification deep learning

来源：评论

学校读者我要写书评

暂无评论

SPIDER:Speeding up Side-Channel Vulnerability Detection via Test Suite Reduction

引用

Tsinghua Science and Technology 2023年第1期28卷 47-58页

作者： Fei Yan Rushan Wu Liqiang Zhang Yue Cao Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan 430072China

Side-channel attacks allow adversaries to infer sensitive information,such as cryptographic keys or private user data,by monitoring unintentional information leaks of running *** side-channel detection methods can identify numerous potential vulnerabilities in cryptographic implementations with a small amount of execution traces due to the high diffusion of secret inputs in crypto ***,because non-cryptographic programs cover different paths under various sensitive inputs,extending existing tools for identifying information leaks to non-cryptographic applications suffers from either insufficient path coverage or redundant *** address these limitations,we propose a new dynamic analysis framework named SPIDER that uses fuzzing,execution profiling,and clustering for a high path coverage and test suite reduction,and then speeds up the dynamic analysis of side-channel vulnerability detection in non-cryptographic *** analyze eight non-cryptographic programs and ten cryptographic algorithms under SPIDER in a fully automated way,and our results confirm the effectiveness of test suite reduction and the vulnerability detection accuracy of the whole framework.

关键词： side-channel detection test suite reduction dynamic analysis

来源：评论

学校读者我要写书评

暂无评论

Edge Guided Network with Motion Enhancement for Few-Shot Action Recognition

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5331-5342页

作者： Du, Kaiwen Ye, Weirong Guo, Hanyu Yan, Yan Wang, Hanzi Huawei Technologies Hangzhou310051 China Ministry of Education of China Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen361005 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China

Existing state-of-the-art methods for few-shot action recognition (FSAR) achieve promising performance by spatial and temporal modeling. However, most current methods ignore the importance of edge information and motion cues, leading to inferior performance. For the few-shot task, it is important to effectively explore limited data. Additionally, effectively utilizing edge information is beneficial for exploring motion cues, and vice versa. In this paper, we propose a novel edge guided network with motion enhancement (EGME) for FSAR. To the best of our knowledge, this is the first work to utilize the edge information as guidance in the FSAR task. Our EGME contains two crucial components, including an edge information extractor (EIE) and a motion enhancement module (ME). Specifically, EIE is used to obtain edge information on video frames. Afterward, the edge information is used as guidance to fuse with the frame features. In addition, ME can adaptively capture motion-sensitive features of videos. It adopts a self-gating mechanism to highlight motion-sensitive regions in videos from a large temporal receptive field. Based on the above designed components, EGME can capture edge information and motion cues, resulting in superior recognition performance. Experimental results on four challenging benchmarks show that EGME performs favorably against recent advanced methods. © 1991-2012 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

Distribution-flexible subset quantization for post-quantizing super-resolution networks

引用

Science China(Information Sciences) 2025年第3期68卷 163-180页

作者： Yunshan ZHONG Mingbao LIN Jingjing XIE Yuxin ZHANG Fei CHAO Rongrong JI Institute of Artificial Intelligence Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of ChinaXiamen University Tencent Youtu Lab Department of Artificial Intelligence School of Informatics Xiamen University Peng Cheng Laboratory

This paper introduces distribution-flexible subset quantization(DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current super-resolution models, which exhibit significant variance across samples and channels. To address this issue, DFSQ conducts channel-wise normalization of the activations and applies distribution-flexible subset quantization(SQ), wherein the quantization points are selected from a universal set consisting of multi-word additive log-scale values. To expedite the selection of quantization points in SQ, we propose a fast quantization points selection strategy that uses K-means clustering to select the quantization points closest to the centroids. Compared to the common iterative exhaustive search algorithm, our strategy avoids the enumeration of all possible combinations in the universal set, reducing the time complexity from exponential to linear. Consequently, the constraint of time costs on the size of the universal set is greatly relaxed. Extensive evaluations of various super-resolution models show that DFSQ effectively improves performance even without fine-tuning. For example, for 4-bit EDSR×2 on the Urban benchmark, DFSQ obtains 0.242 dB PSNR gains.

关键词： super-resolution post-training quantization distribution-flexible subset quantization neural network

来源：评论

学校读者我要写书评

暂无评论

Omni-Detection of Adversarial Examples with Diverse Magnitudes

引用

China Communications 2024年第12期21卷 139-151页

作者： Ke Jianpeng Wang Wenqi Yang Kang Wang Lina Ye Aoshuang Wang Run Key Laboratory of Aerospace Information Security and Trusted Computing(Wuhan University) Ministry of EducationWuhan 430072China School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China

Deep neural networks(DNNs)are poten-tially susceptible to adversarial examples that are ma-liciously manipulated by adding imperceptible pertur-bations to legitimate inputs,leading to abnormal be-havior of *** of methods have been pro-posed to defend against adversarial ***-ever,the majority of them are suffering the follow-ing weaknesses:1)lack of generalization and prac-ticality.2)fail to deal with unknown *** ad-dress the above issues,we design the adversarial na-ture eraser(ANE)and feature map detector(FMD)to detect fragile and high-intensity adversarial examples,***,we apply the ensemble learning method to compose our detector,dealing with adver-sarial examples with diverse magnitudes in a divide-and-conquer *** results show that our approach achieves 99.30%and 99.62%Area un-der Curve(AUC)scores on average when tested with various Lp norm-based attacks on CIFAR-10 and Im-ageNet,***,our approach also shows its potential in detecting unknown attacks.

关键词： adversarial example detection ensemble learning feature maps fragile and high-intensity ad-versarial examples

来源：评论

学校读者我要写书评

暂无评论

DiagnoCare: A Diagnostic Analysis System for Electronic Medical Records Combining Medical Knowledge Graph and Large Language Model 10

DiagnoCare: A Diagnostic Analysis System for Electronic Medi...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Huang, Shiwang Luo, Guofeng Wang, Jiaru Chen, Longbiao Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart Cities China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen China

ISBN: (纸本)9798331520861

With the rapid development of healthcare technologies and the increasing demand for intelligent diagnostic systems, we present a novel approach that combines medical knowledge graphs and Large Language Models (LLMs) for enhanced Electronic Medical Record (EMR) analysis and condition warning. Our system integrates structured medical knowledge with advanced text analysis capabilities to accurately interpret and process complex EMR data. By leveraging LLMs and prompt learning, the system provides personalized examination suggestions, diagnostic analyses, and disease warnings. Experimental results on real-world datasets, including the MIMIC III database and anonymized hospital records from Fujian Province, China, demonstrate the system's efficacy in delivering precise and actionable insights. Case studies further illustrate the system's practical value and usability, highlighting its potential to significantly improve clinical decision-making and patient outcomes. This research offers substantial implications for the advancement of intelligent EMR systems and personalized healthcare. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models

Code Membership Inference for Detecting Unauthorized Data Us...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Sheng Li, Hui Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China

ISBN: (纸本)9798891761681

Code pre-trained language models (CPLMs) have received great attention since they can benefit various tasks that facilitate software development and maintenance. However, CPLMs are trained on massive open-source code, raising concerns about potential data infringement. This paper launches the study of detecting unauthorized code use in CPLMs, i.e., Code Membership Inference (CMI) task. We design a framework BUZZER for different settings of CMI. BUZZER deploys several inference techniques, including signal extraction from pre-training tasks, hard-to-learn sample calibration and weighted inference, to identify code membership status accurately. Extensive experiments show that CMI can be achieved with high accuracy using BUZZER. Hence, BUZZER can serve as a CMI tool and help protect intellectual property rights. The implementation of BUZZER is available at: https://***/KDEGroup/Buzzer. © 2024 Association for Computational Linguistics.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Quantum Attacks on Type-3 Generalized Feistel Scheme and Unbalanced Feistel Scheme with Expanding Functions

引用

Chinese Journal of Electronics 2023年第2期32卷 209-216页

作者： ZHANG Zhongya WU Wenling SUI Han WANG Bolin Trusted Computing and Information Assurance Laboratory Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Luoyang Normal University State Key Laboratory of Cryptology

Quantum algorithms are raising concerns in the field of cryptography all over the world. A growing number of symmetric cryptography algorithms have been attacked in the quantum setting. Type-3 generalized Feistel scheme(GFS) and unbalanced Feistel scheme with expanding functions(UFS-E) are common symmetric cryptography schemes, which are often used in cryptographic analysis and design. We propose quantum distinguishing attacks on Type-3 GFS and UFS-E in the quantum chosen plaintext attack setting. The results of key recovery are better than those based on exhaustive search in the quantum setting.

关键词： Quantum algorithm Cryptography

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：