检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Jiang, Bo Liu, Ya-Feng Ministry of Education Key Laboratory of NSLSCS School of Mathematical Sciences Nanjing Normal University Nanjing210023 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781713899921

Projection robust Wasserstein (PRW) distance is recently proposed to efficiently mitigate the curse of dimensionality in the classical Wasserstein distance. In this paper, by equivalently reformulating the computation of the PRW distance as an optimization problem over the Cartesian product of the Stiefel manifold and the Euclidean space with additional nonlinear inequality constraints, we propose a Riemannian exponential augmented Lagrangian method (REALM) for solving this problem. Compared with the existing Riemannian exponential penalty-based approaches, REALM can potentially avoid too small penalty parameters and exhibit more stable numerical performance. To solve the subproblems in REALM efficiently, we design an inexact Riemannian Barzilai-Borwein method with Sinkhorn iteration (iRBBS), which selects the stepsizes adaptively rather than tuning the stepsizes in efforts as done in the existing methods. We show that iRBBS can return an Ε-stationary point of the original PRW distance problem within O(Ε-3) iterations, which matches the best known iteration complexity result. Extensive numerical results demonstrate that our proposed methods outperform the state-of-the-art solvers for computing the PRW distance. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Soups: Improving Transferability and Stealthiness for Free

arXiv

引用

arXiv 2024年

作者： Yang, Bo Zhang, Hengwei Wang, Jindong Yang, Yulong Lin, Chenhao Shen, Chao Zhao, Zhengyu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an China

Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing transferability is to keep only the optimal adversarial example from all those obtained in the optimization pipeline. In this paper, for the first time, we question this convention and demonstrate that those discarded, sub-optimal adversarial examples can be reused to boost transferability. Specifically, we propose "Adversarial Example Soups" (AES), with AES-tune for averaging discarded adversarial examples in hyperparameter tuning and AES-rand for stability testing. In addition, our AES is inspired by "model soups", which averages weights of multiple fine-tuned models for improved accuracy without increasing inference time. Extensive experiments validate the global effectiveness of our AES, boosting 10 state-of-the-art transfer attacks and their combinations by up to 13% against 10 diverse (defensive) target models. We also show the possibility of generalizing AES to other types, e.g., directly averaging multiple in-the-wild adversarial examples that yield comparable success. A promising byproduct of AES is the improved stealthiness of adversarial examples since the perturbation variances are naturally reduced. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Causal Reasoning Ability of Open Large Language Model: A Comprehensive and Exemplary Functional Testing

The Causal Reasoning Ability of Open Large Language Model: A...

引用

IEEE International Conference on Software Quality, Reliability and Security (QRS)

作者： Shun-Hang Li Gang Zhou Zhi-Bo Li Ji-Cang Lu Ning-Bo Huang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China Information Engineering University Zhengzhou China

As the intelligent software, the development and application of large language models are extremely hot topics recently, bringing tremendous changes to general AI and software industry. Nonetheless, large language models, especially open source ones, incontrollably suffer from some potential software quality issues such as instability, inaccuracy, and insecurity, making software testing necessary. In this paper, we propose the first solution for functional testing of open large language models to check full-scene availability and conclude empirical principles for better steering large language models, particularly considering their black box and intelligence properties. Specifically, we focus on the model’s causal reasoning ability, which is the core of artificial intelligence but almost ignored by most previous work. First, for comprehensive evaluation, we deconstruct the causal reasoning capability into five dimensions and summary the forms of causal reasoning task as causality identification and causality matching. Then, rich datasets are introduced and further modified to generate test cases along with different ability dimensions and task forms to improve the testing integrity. Moreover, we explore the ability boundary of open large language models in two usage modes: prompting and lightweight fine-tuning. Our work conducts comprehensive functional testing on the causal reasoning ability of open large language models, establishes benchmarks, and derives empirical insights for practical usage. The proposed testing solution can be transferred to other similar evaluation tasks as a general framework for large language models or their derivations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ERROR ANALYSIS OF FRACTIONAL COLLOCATION METHODS FOR VOLTERRA INTEGRO-DIFFERENTIAL EQUATIONS WITH NONCOMPACT OPERATORS

引用

Journal of Computational Mathematics 2025年第3期43卷 690-707页

作者： Zheng Ma Chengming Huang Anatoly A.Alikhanov School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China North-Caucasus Center for Mathematical Research North-Caucasus Federal UniversityStavropol 355017Russia North-Eastern Federal University Yakutsk 677000Russia

This paper is concerned with the numerical solution of Volterra integro-differential equations with noncompact *** focus is on the problems with weakly singular *** handle the initial weak singularity of the solution,a fractional collocation method is applied.A rigorous hp-version error analysis of the numerical method under a weighted H1-norm is carried *** result shows that the method can achieve high order convergence for such *** experiments are also presented to confirm the effectiveness of the proposed method.

关键词： Volterra integro-differential equation Noncompact operator Nonsmooth solution Collocation method Fractional polynomial hp-version error analysis

来源：评论

学校读者我要写书评

暂无评论

On the Cycle Structure of Some Nonlinear Feedback Shift Registers

引用

Chinese Journal of Electronics 2025年第4期23卷 801-804页

作者： Zhongxiao Wang Hong Xu Wenfeng Qi State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Information Science and Technology Institute Zhengzhou China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

In this paper, we partly determine the cycle structure of two types of Nonlinear feedback shift registers (NFSRs). Based on these results, the cycle structure of a class of NFSRs with symmetric feedback functions can be completely characterized. Furthermore, an alternative proof of Kjeldsen's results is presented. Compared with the original proof based on abstract algebra theory, ours is straightforward and easy to understand.

关键词： Abstract algebra Shift registers Cryptography

来源：评论

学校读者我要写书评

暂无评论

Polytopic Attack on Round-Reduced Simon32/64 Using Deep Learning 16th

Polytopic Attack on Round-Reduced Simon32/64 Using Deep Lear...

引用

16th International Conference on Information Security and Cryptology, Inscrypt 2020

作者： Su, Heng-Chuan Zhu, Xuan-Yong Ming, Duan State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University Zhengzhou450001 China

ISBN: (纸本)9783030718510

In CRYPTO 2019, Gohr uses the residual network technology of artificial intelligence to build a differential distinguisher, and attacks the reduced-round Speck32/64. We tried this method to recover the keys for ten-round Simon32/64. In this paper, we have three innovations. First, we construct polytope neural network distinguisher. On eight-round Simon32/64, polytope neural network distinguisher could increase the success rate of three neural network distinguishers with 0.76 success rate to 0.92. Second, we propose an attack on Simon32/64 based on the combination of the probability of differential path and polytope neural network distinguisher. This method can only increase the computational complexity of the chosen data as the number of rounds increases. Nine-round polytope neural network distinguisher is used to filter out data, whether it is what we want. Eight-round neural distinguisher is used to recover the final round key. The computational complexity of key recovery on the final key of eleven-round Simon32/64 is 233.4. Third, we propose an attack called Bayesian key Research with Error. With this attack, the computational complexity of key recovery on the final key of eleven-round Simon32/64 is 230.9. In our paper, the main idea is combining polytope differences with neural networks. By constructing polytope differential neural network distinguisher, we make a key recovery attack. In order to increase the number of rounds, we first used brute force attack and then proposed Bayesian key Research with Error. We think this idea can be applied to many cryptographic algorithms. © 2021, Springer Nature Switzerland AG.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Selection Strategy for Network Security Defense Based on a Time Game Model

A Selection Strategy for Network Security Defense Based on a...

引用

2021 International Conference on Digital Society and Intelligent Systems, DSInS 2021

作者： Sun, Pengyu Zhang, Hengwei Ma, Junqiang Li, Chenwei Mi, Yan Wang, Jindong Key Laboratory of Information Security of Henan Provincial State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665406307

Current network assessment models often ignore the impact of attack-defense timing on network security, making it difficult to characterize the dynamic game of attack-defense effectively. To effectively manage the network security risks and reduce potential losses, in this article, we propose a selection strategy for network defense based on a time game model. By analyzing the attack-defense status by analogy with the SIR infectious disease model, construction of an optimal defense strategy model based on time game, and calculation of the Nash equilibrium of the the attacker and the defender under different strategies, we can determine an optimal defense strategy. With the Matlab simulation, this strategy is verified to be effective. © 2021 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Timing Strategy for Active Detection of APT Attack Based on FlipIt Model and Q-learning Method

Timing Strategy for Active Detection of APT Attack Based on ...

引用

2021 International Conference on Digital Society and Intelligent Systems, DSInS 2021

作者： Liu, Zhilin Zhang, Hengwei Sun, Pengyu Mi, Yan Zhang, Xiaoning Wang, Jindong Key Laboratory of Information Security of Henan Provincial State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665406307

At present, APT attack detection mainly focuses on the specific realization of detection technology, and there is little research on the timing strategy for active detection of APT attack. This paper focuses on the problem of APT dynamic detection with timing decision intelligence. We use the FlipIt game model and reinforcement learning method of Q-learning algorithm, consider the APT attack events as an exponentially distributed random process, and the defender using the attacker's last move time (LM-defender) to learn his optimal timing strategy using Q-Learning algorithm. The defender's reinforcement learning mechanism for the timing of the APT attack action and outputs its timing selection strategy. Simulation experiments show that compared with the existing greedy algorithm, the timing strategy based on the Q-Learning algorithm does not require the attacker's prior information under the premise, it can achieve a higher average benefit than the greedy strategy. This result provides a theoretical reference for the design of timing strategy to defend APT attack intelligently and efficient. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Network Attack Intention Recognition Based on Signaling Game Model and Netlogo Simulation

Network Attack Intention Recognition Based on Signaling Game...

引用

2021 International Conference on Digital Society and Intelligent Systems, DSInS 2021

作者： Zhang, Xiaoning Zhang, Hengwei Li, Chenwei Sun, Pengyu Liu, Zhilin Wang, Jindong State Key Laboratory of Mathematical Engineering and Advanced Computing Key Laboratory of Information Security of Henan Provincial Zhengzhou China

ISBN: (纸本)9781665406307

With the development of attack technology, identifying the real intention of network attack and avoiding further deterioration of security situation has become a hot research topic in recent years. This paper proposes an attack intention recognition method based on signaling game model. Firstly, we generate attack intention hypotheses, and then calculate the probability of each attack intention by solving game equilibrium. Experiments show that the method can effectively improve the accuracy of attack intention recognition from the perspective of the revenue. © 2021 IEEE.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Imputing DNA Methylation by Transferred Learning Based Neural Network

引用

Journal of Computer Science & Technology 2022年第2期37卷 320-329页

作者： Xin-Feng Wang Xiang Zhou Jia-Hua Rao Zhu-Jin Zhang Yue-Dong Yang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510000China Key Laboratory of Machine Intelligence and Advanced Computing of Ministry of Education(Sun Yat-sen University)Guangzhou 510000 China

DNA methylation is one important epigenetic type to play a vital role in many diseases including *** the development of the high-throughput sequencing technology,there is much progress to disclose the relations of DNA methylation with ***,the analyses of DNA methylation data are challenging due to the missing values caused by the limitations of current *** many methods have been developed to impute the missing values,these methods are mostly based on the correlations between individual samples,and thus are limited for the abnormal samples in *** this study,we present a novel transfer learning based neural network to impute missing DNA methylation data,namely the TDimpute-DNAmeth *** method learns common relations between DNA methylation from pan-cancer samples,and then fine-tunes the learned relations over each specific cancer type for imputing the missing *** on 16 cancer datasets,our method was shown to outperform other commonly-used *** analyses indicated that DNA methylation is related to cancer survival and thus can be used as a biomarker of cancer prognosis.

关键词： neural network transfer learning DNA methylation data imputation survival analysis

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：