检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Wan, Yuanyu Yao, Chang Song, Mingli Zhang, Lijun The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Software Technology Zhejiang University Ningbo China Institute of Blockchain and Data Security Hangzhou China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Online convex optimization (OCO) with arbitrary delays, in which gradients or other information of functions could be arbitrarily delayed, has received increasing attention recently. Different from previous studies that focus on stationary environments, this paper investigates the delayed OCO in non-stationary environments, and aims to minimize the dynamic regret with respect to any sequence of comparators. To this end, we first propose a simple algorithm, namely DOGD, which performs a gradient descent step for each delayed gradient according to their arrival order. Despite its simplicity, our novel analysis shows that the dynamic regret of DOGD can be automatically bounded by (equation presented) under mild assumptions, and (equation presented) in the worst case, where d¯ and d denote the average and maximum delay respectively, T is the time horizon, and PT is the path-length of comparators. Furthermore, we develop an improved algorithm, which reduces those dynamic regret bounds achieved by DOGD to (equation presented), respectively. The key idea is to run multiple DOGD with different learning rates, and utilize a meta-algorithm to track the best one based on their delayed performance. Finally, we demonstrate that our improved algorithm is optimal in the worst case by deriving a matching lower bound. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Regret for Bandit Convex Optimization with Delayed Feedback 38

Improved Regret for Bandit Convex Optimization with Delayed ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wan, Yuanyu Yao, Chang Song, Mingli Zhang, Lijun School of Software Technology Zhejiang University Ningbo China State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

We investigate bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under an arbitrary delay. Let n, T, d¯ denote the dimensionality, time horizon, and average delay, respectively. Previous studies have achieved an O(√nT3/4 +(nd¯)1/3T2/3) regret bound for this problem, whose delay-independent part matches the regret of the classical non-delayed bandit gradient descent algorithm. However, there is a large gap between its delay-dependent part, i.e., O((nd¯)1/3T2/3), and an existing Ω(√d¯T) lower bound. In this paper, we illustrate that this gap can be filled in the worst case, where d¯is very close to the maximum delay d. Specifically, we first develop a novel algorithm, and prove that it enjoys a regret bound of O(√nT3/4 + √dT) in general. Compared with the previous result, our regret bound is better for d = O((nd¯)2/3T1/3), and the delay-dependent part is tight in the worst case. The primary idea is to decouple the joint effect of the delays and the bandit feedback on the regret by carefully incorporating the delayed bandit feedback with a blocking update mechanism. Furthermore, we show that the proposed algorithm can improve the regret bound to O((nT)2/3 log1/3 T + dlog T) for strongly convex functions. Finally, if the action sets are unconstrained, we demonstrate that it can be simply extended to achieve an O(n√T log T + dlog T) regret bound for strongly convex and smooth functions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Library Vulnerability via Migration Based Automating Test Generation 24

Exploiting Library Vulnerability via Migration Based Automat...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Chen, Zirui Hu, Xing Xia, Xin Gao, Yi Xu, Tongtong Lo, David Yang, Xiaohu Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Huawei China Singapore Management University Singapore

ISBN: (纸本)9798400702174

In software development, developers extensively utilize third-party libraries to avoid implementing existing functionalities. When a new third-party library vulnerability is disclosed, project maintainers need to determine whether their projects are affected by the vulnerability, which requires developers to invest substantial effort in assessment. However, existing tools face a series of issues: static analysis tools produce false alarms, dynamic analysis tools require existing tests and test generation tools have low success rates when facing complex vulnerabilities. Vulnerability exploits, as code snippets provided for reproducing vulnerabilities after disclosure, contain a wealth of vulnerability-related information. This study proposes a new method based on vulnerability exploits, called Vesta (Vulnerability Exploit-based Software Testing Auto-Generator), which provides vulnerability exploit tests as the basis for developers to decide whether to update dependencies. Vesta extends the search-based test generation methods by adding a migration step, ensuring the similarity between the generated test and the vulnerability exploit, which increases the likelihood of detecting potential library vulnerabilities in a project. We perform experiments on 30 vulnerabilities disclosed in the past five years, involving 60 vulnerability-project pairs, and compare the experimental results with the baseline method, Transfer. The success rate of Vesta is 71.7% which is a 53.4% improvement over Transfer in the effectiveness of verifying exploitable vulnerabilities. © 2024 ACM.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

HyperMR: Efficient Hypergraph-enhanced Matrix Storage on Compute-in-Memory Architecture

引用

Proceedings of the ACM on Management of data 2025年第1期3卷 1-27页

作者： Yifan Wu Ke Chen Gang Chen Dawei Jiang Huan Li Lidan Shou The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China & Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China

Matrix-vector multiplication (MVM) operations, essential for modern hardware architectures, suffer from heavy I/O overheads and costly serial multiply-add operations. The emerging Compute-in-Memory (CIM) architecture alleviates these issues by enabling in situ MVM operations with O(1) time complexity, eliminating the need to move matrices. However, current storage schemes are still inefficient on CIM due to limited optimization objectives and inflexible support for various access patterns and matrix structures. To address this, we propose HyperMR, a hypergraph-enhanced matrix storage scheme for CIM architectures. First, we identify two performance optimization objectives that are tailored to CIM and prove their NP-hardness. We then introduce a hypergraph modeling approach with a novel access-aware hypergraph generation algorithm to handle diverse matrix structures and access patterns. Moreover, we present a two-phase hypergraph partitioning method to efficiently tackle the NP-hard optimization objectives. Experimental results show that HyperMR outperforms multiple state-of-the-art storage schemes, offering valid optimization for all evaluated matrices, compared to the best-performing baseline which optimizes only 75%. HyperMR also achieves the best average optimization performance for matrix storage layouts, significantly improving efficiency in varied workload scenarios, with a 29.65% improvement on synthetic queries and up to 34.9% on scientific image filtering.

关键词： compute-in-memory architecture emerging hardware matrix storage scientific data management

来源：评论

学校读者我要写书评

暂无评论

Streamlining Java Programming: Uncovering Well-Formed Idioms with Idiomine 24

Streamlining Java Programming: Uncovering Well-Formed Idioms...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Yang, Yanming Hu, Xing Xia, Xin Lo, David Yang, Xiaohu Zhejiang University The State Key Laboratory of Blockchain and Data Security China Zhejiang University China Singapore Management University Singapore

ISBN: (纸本)9798400702174

Code idioms are commonly used patterns, techniques, or practices that aid in solving particular problems or specific tasks across multiple software projects. They can improve code quality, performance, and maintainability, and also promote program standardization and reuse across projects. However, identifying code idioms is significantly challenging, as existing studies have still suffered from three main limitations. First, it is difficult to recognize idioms that span non-contiguous code lines. Second, identifying idioms with intricate data flow and code structures can be challenging. More-over, they only extract dataset-specific idioms, so common idioms or well-established code/design patterns that are rarely found in datasets cannot be identified. To overcome these limitations, we propose a novel approach, named Idiomine, to automatically extract generic and specific idioms from both Java projects and libraries. We perform program analysis on Java functions to transform them into concise PDGs, for integrating the data flow and control flow of code fragments. We then develop a novel chain structure, data-driven Control Chain (DCC), to extract sub-idioms that possess contiguous semantic meanings from PDGs. After that, we utilize GraphCodeBERT to generate code embeddings of these sub-idioms and perform density-based clustering to obtain frequent sub-idioms. We use heuristic rules to identify interrelated sub-idioms among the frequent ones. Finally, we employ ChatGPT to synthesize interrelated sub-idioms into potential code idioms and infer real idioms from them. We conduct well-designed experiments and a user study to evaluate Idiomine's correctness and the practical value of the extracted idioms. Our experimental results show that Idiomine effectively extracts more idioms with better performance in most metrics. We compare our approach with Haggis and ChatGPT, Idiomine outperforms them by 22.8% and 35.5% in Idiom Set Precision (ISP) and by 9.7% and 22.9% in Idiom

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks 38

Dual-Perspective Activation: Efficient Channel Denoising via...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Qiu, Tian Gao, Chenchao Feng, Zunlei Lei, Jie Hu, Bingde Wang, Xingen Gao, Yi Song, Mingli State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Dalian University of Technology China Zhejiang University of Technology China Bangsheng Technology Co. Ltd. China

The design of Artificial Neural Network (ANN) is inspired by the working patterns of the human brain. Connections in biological neural networks are sparse, as they only exist between few neurons. Meanwhile, the sparse representation in ANNs has been shown to possess significant advantages. Activation responses of ANNs are typically expected to promote sparse representations, where key signals get activated while irrelevant/redundant signals are suppressed. It can be observed that samples of each category are only correlated with sparse and specific channels in ANNs. However, existing activation mechanisms often struggle to suppress signals from other irrelevant channels entirely, and these signals have been verified to be detrimental to the network's final decision. To address the issue of channel noise interference in ANNs, a novel end-to-end trainable Dual-Perspective Activation (DPA) mechanism is proposed. DPA efficiently identifies irrelevant channels and applies channel denoising under the guidance of a joint criterion established online from both forward and backward propagation perspectives while preserving activation responses from relevant channels. Extensive experiments demonstrate that DPA successfully denoises channels and facilitates sparser neural representations. Moreover, DPA is parameter-free, fast, applicable to many mainstream ANN architectures, and achieves remarkable performance compared to other existing activation counterparts across multiple tasks and domains. Code is available at https://***/horrible-dong/DPA. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models

Cross-modality Information Check for Detecting Jailbreaking ...

引用

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

作者： Xu, Yue Qi, Xiuyuan Qin, Zhan Wang, Wenjie School of Information Science and Technology ShanghaiTech University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China

ISBN: (纸本)9798891761681

Multimodal Large Language Models (MLLMs) extend the capacity of LLMs to understand multimodal information comprehensively, achieving remarkable performance in many vision-centric tasks. Despite that, recent studies have shown that these models are susceptible to jailbreak attacks, which refer to an exploitative technique where malicious users can break the safety alignment of the target model and generate misleading and harmful answers. This potential threat is caused by both the inherent vulnerabilities of LLM and the larger attack scope introduced by vision input. To enhance the security of MLLMs against jailbreak attacks, researchers have developed various defense techniques. However, these methods either require modifications to the model's internal structure or demand significant computational resources during the inference phase. Multimodal information is a double-edged sword. While it increases the risk of attacks, it also provides additional data that can enhance safeguards. Inspired by this, we propose Cross-modality Information DEtectoR (CIDER), a plug-and-play jailbreaking detector designed to identify maliciously perturbed image inputs, utilizing the cross-modal similarity between harmful queries and adversarial images. CIDER is independent of the target MLLMs and requires less computation cost. Extensive experimental results demonstrate the effectiveness and efficiency of CIDER, as well as its transferability to both white-box and black-box MLLMs. The resource is available at https://***/PandragonXIII/CIDER. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators 31

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

blockchain and signcryption enabled asynchronous federated learning framework in fog computing

引用

Digital Communications and Networks 2025年第2期11卷 442-454页

作者： Zhou Zhou Youliang Tian Jinbo Xiong Changgen Peng Jing Li Nan Yang State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber SecurityFujian Normal UniversityFuzhou 350117China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic TechnologyGuilin 541004China

Federated learning combines with fog computing to transform data sharing into model sharing,which solves the issues of data isolation and privacy disclosure in fog ***,existing studies focus on centralized single-layer aggregation federated learning architecture,which lack the consideration of cross-domain and asynchronous robustness of federated learning,and rarely integrate verification mechanisms from the perspective of *** address the above challenges,we propose a blockchain and Signcryption enabled Asynchronous Federated Learning(BSAFL)framework based on dual aggregation for cross-domain *** particular,we first design two types of signcryption schemes to secure the interaction and access control of collaborative learning between ***,we construct a differential privacy approach that adaptively adjusts privacy budgets to ensure data privacy and local models'availability of intra-domain ***,we propose an asynchronous aggregation solution that incorporates consensus verification and elastic participation using ***,security analysis demonstrates the security and privacy effectiveness of BSAFL,and the evaluation on real datasets further validates the high model accuracy and performance of BSAFL.

关键词： blockchain Signcryption Federated learning Asynchronous Fog computing

来源：评论

学校读者我要写书评

暂无评论

Dual Prompt-Based Few-Shot Learning for Automated Vulnerability Patch Localization 31

Dual Prompt-Based Few-Shot Learning for Automated Vulnerabil...

引用

31st IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2024

作者： Zhang, Junwei Hu, Xing Bao, Lingfeng Xia, Xin Li, Shanping Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Software Engineering Application Technology Lab Huawei China

ISBN: (纸本)9798350330663

Vulnerabilities are disclosed with corresponding patches so that users can remediate them in time. However, there are instances where patches are not released with the disclosed vulnerabilities, causing hidden dangers, especially if dependent software remains uninformed about the affected code repository. Hence, it is crucial to automatically locate security patches for disclosed vulnerabilities among a multitude of commits. Despite the promising performance of existing learning-based localization approaches, they still suffer from the following limitations: (1) They cannot perform well in data scarcity scenarios. Most neural models require extensive datasets to capture the semantic correlations between the vulnerability description and code commits, while the number of disclosed vulnerabilities with patches is limited. (2) They struggle to capture the deep semantic correlations between the vulnerability description and code commits due to inherent differences in semantics and characters between code changes and commit messages. It is difficult to use one model to capture the semantic correlations between vulnerability descriptions and code commits. To mitigate these two limitations, in this paper, we propose a novel security patch localization approach named Prom VPat, which utilizes the dual prompt tuning channel to capture the semantic correlation between vulnerability descriptions and commits, especially in data scarcity (i.e., few-shot) scenarios. We first input the commit message and code changes with the vulnerability description into the prompt generator to generate two new inputs with prompt templates. Then, we adopt a pre-trained language model (i.e., PLM) as the encoder, utilize the prompt tuning method to fine-tune the encoder, and generate two correlation probabilities as the semantic features. In addition, we extract 26 handcrafted features from the vulnerability descriptions and the code commits. Finally, we utilize the attention mechanism to fuse the

关键词： Semantics

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：