检索结果-内蒙古大学图书馆

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Li, Zhiqiang Chen, Yonghong Teng, Zhan Huang, Xuwen School of Computer Science and Technology Huaqiao University Xiamen Fujian China Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University Xiamen Fujian China

ISBN: (纸本)9798400700705

A covert timing channel is a technical means that enables information hiding and covert communication. Due to the fact that covert timing channels can elude detection by security defence measures, they offer a substantial security risk to the information of Internet users when they are exploited for illicit reasons. The attacker sends at a low rate to ensure the stealthiness of the covert timing channel communication process, making the number of inter-arrival time encoded as covert information much less than the normal number of inter-arrival time, resulting in the low detection accuracy of existing detection methods. In this paper, we propose a covert timing channel detection method based on one-dimensional convolution and self-attention mechanism. The method begins with local feature extraction of the input inter-arrival time sequence by a one-dimensional convolutional layer, then characterizes the correlation between each inter-arrival time by a self-attention mechanism in the encoder, and finally through the full connection layer to produce the type output. In this study, experimental results on a public dataset and 16 self-built datasets demonstrate that the detection method delivers optimal detection results and efficient detection of covert information in low-volume communications. © 2023 ACM.

关键词： Optimal detection

来源：评论

学校读者我要写书评

暂无评论

Verified Lifting of Deep learning Operators

arXiv

引用

arXiv 2024年

作者： Zhan, Qi Hu, Xing Xia, Xin Li, Shanping The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Zhejiang University Hangzhou China

Deep learning operators are fundamental components of modern deep learning frameworks. With the growing demand for customized operators, it has become increasingly common for developers to create their own. However, designing and implementing operators is complex and error-prone, due to hardware-specific optimizations and the need for numerical stability. There is a pressing need for tools that can summarize the functionality of both existing and user-defined operators. To address this gap, this work introduces a novel framework for the verified lifting of deep learning operators, which synthesizes high-level mathematical formulas from low-level implementations. Our approach combines symbolic execution, syntax-guided synthesis, and SMT-based verification to produce readable and formally verified mathematical formulas. In synthesis, we employ a combination of top-down and bottom-up strategies to explore the vast search space efficiently;In verification, we design invariant synthesis patterns and leverage SMT solvers to validate the correctness of the derived summaries;In simplification, we use egraph-based techniques with custom rules to restore complex formulas to their natural, intuitive forms. Evaluated on a dataset of deep learning operators implemented in Triton from the real world, our method demonstrates the effectiveness of synthesis and verification compared to existing techniques. This framework bridges the gap between low-level implementations and high-level abstractions, improving understanding and reliability in deep learning operator development. © 2024, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards More Practical Automation of Vulnerability Assessment

Towards More Practical Automation of Vulnerability Assessmen...

引用

International Conference on Software Engineering (ICSE)

作者： Shengyi Pan Lingfeng Bao Jiayuan Zhou Xing Hu Xin Xia Shanping Li The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou Zhejiang China Centre for Software Excellence Huawei Kingston Ontario Canada The State Key Laboratory of Blockchain and Data Security Zhejiang University Ningbo Zhejiang China Huawei Hangzhou Zhejiang China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

It is increasingly suggested to identify emerging software vulner-abilities (SVs) through relevant development activities (e.g., issue reports) to allow early warnings to open source software (OSS) users. However, the support for the following assessment of the de-tected SVs has not yet been explored. SV assessment characterizes the detected SVs to prioritize limited remediation resources on the critical ones. To fill this gap, we aim to enable early vulnerability assessment based on SV-related issue reports (SIR). Besides, we observe the following concerns of the existing assessment techniques: 1) the assessment output lacks rationale and practical value; 2) the associations between Common Vulnerability Scoring System (CVSS) metrics have been ignored; 3) insufficient evaluation sce-narios and metrics. We address these concerns to enhance the prac-ticality of our proposed early vulnerability assessment approach (namely proEVA). Specifically, based on the observation of strong associations between CVSS metrics, we propose a prompt-based model to exploit such relations for CVSS metrics prediction. More-over, we design a curriculum-learning (CL) schedule to guide the model better learn such hidden associations during training. Aside from the standard classification metrics adopted in existing works, we propose two severity-aware metrics to provide a more compre-hensive evaluation regarding the prioritization of the high-severe SVs. Experimental results show that proEVA significantly outper-forms the baselines in both types of metrics. We further discuss the transferability of the prediction model regarding the upgrade of the assessment system, an important yet overlooked evaluation scenario in existing works. The results verify that proEVA is more efficient and flexible in migrating to different assessment systems.

关键词： Measurement Training Schedules Automation Predictive models Standards Open source software

来源：评论

学校读者我要写书评

暂无评论

On the trajectory regularity of ODE-based diffusion sampling 24

On the trajectory regularity of ODE-based diffusion sampling

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Defang Chen Zhenyu Zhou Can Wang Chunhua Shen Siwei Lyu State Key Laboratory of Blockchain and Data Security Zhejiang University China and Hangzhou High-Tech Zone (Binjiang) Blockchain and Data Security Research Institute China Zhejiang University China University at Buffalo

Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models. We characterize an implicit denoising trajectory and discuss its vital role in forming the coupled sampling trajectory with a strong shape regularity, regardless of the generated content. We also describe a dynamic programming-based scheme to make the time schedule in sampling better fit the underlying trajectory structure. This simple strategy requires minimal modification to any given ODE-based numerical solvers and incurs negligible computational cost, while delivering superior performance in image generation, especially in 5 ∼ 10 function evaluations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Reentrancy Vulnerability Detection and Repair with a Hybrid Model Framework

Enhancing Reentrancy Vulnerability Detection and Repair with...

引用

Asia-Pacific Conference on Software Engineering

作者： Mengliang Li Xiaoxue Ren Han Fu Zhuo Li Jianling Sun State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security College of Computer Science and Technology Zhejiang University State Street Technology(Zhejiang) Ltd

ISBN: (数字)9798331534011

ISBN: (纸本)9798331534028

Smart contracts bring revolutionary changes to the credit landscape. However, their security remains intensely scrutinized due to numerous hacking incidents and inherent logical challenges. One well-known and representative issue is reentrancy vulnerability, exemplified by DAO attacks that lead to substantial economic losses. Conventional approaches to detecting and repairing reentrancy vulnerability often suffer from numerous limitations, including disregarding the intricate vulnerability features and the overfitting problems associated with imbalanced datasets. Large language models are distinguished for their excellent language understanding and have achieved explosive success in artificial intelligence. However, direct prompt-based LLMs-driven approaches for reentrancy vulnerability are plagued by inefficiencies and a lack of domain-specific vulnerability knowledge. This paper proposes a hybrid framework to enhance reentrancy vulnerability detection and repair and safeguard smart contract security. This unified framework comprises two crucial modules: enhanced DL-driven vulnerability detection and knowledge-aware LLMs-driven vulnerability repair. Our approach can significantly enhance reentrancy vulnerability detection and repair efficiency by integrating advanced techniques such as feature extraction, data balancing, deep learning networks, and knowledge-aware prompting. Extensive experimental results validate the superiority of our approach over state-of-the-art baselines, emphasizing its potential to fortify the security of smart contracts and blockchain-based systems. For instance, our approach can achieve 3.51 %, 2.31 %, 0.42%, and 0.85 % improvements in accuracy, recall, precision, and F1 score while detecting reentrancy vulnerability. Additionally, our approach also can achieve a 9.62% improvement in reentrancy vulnerability repair.

关键词： Deep learning Codes Large language models Smart contracts Maintenance engineering Syntactics Feature extraction Classification algorithms security Software engineering

来源：评论

学校读者我要写书评

暂无评论

CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition

arXiv

引用

arXiv 2023年

作者： Peng, Cheng Chen, Ke Shou, Lidan Chen, Gang The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou310000 China

Multi-modal multi-label emotion recognition (MMER) aims to identify relevant emotions from multiple modalities. The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data. Recent studies are mainly devoted to exploring various fusion strategies to integrate multi-modal information into a unified representation for all labels. However, such a learning scheme not only overlooks the specificity of each modality but also fails to capture individual discriminative features for different labels. Moreover, dependencies of labels and modalities cannot be effectively modeled. To address these issues, this paper presents ContrAstive feature Reconstruction and AggregaTion (CARAT) for the MMER task. Specifically, we devise a reconstruction-based fusion mechanism to better model fine-grained modality-to-label dependencies by contrastively learning modal-separated and label-specific features. To further exploit the modality complementarity, we introduce a shuffle-based aggregation strategy to enrich co-occurrence collaboration among labels. Experiments on two benchmark datasets CMU-MOSEI and M3ED demonstrate the effectiveness of CARAT over state-of-the-art methods. Code is available at https://***/chengzju/CARAT. Copyright © 2023, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Holistic Semantic Representation for Navigational Trajectory Generation 39

Holistic Semantic Representation for Navigational Trajectory...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cao, Ji Zheng, Tongya Guo, Qinghong Wang, Yu Dai, Junshu Liu, Shunyu Yang, Jie Song, Jie Song, Mingli Zhejiang University China Big Graph Center Hangzhou City University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Nanyang Technological Univerisity Singapore Institute of Blockchain and Data Security China

ISBN: (纸本)157735897X

Trajectory generation has garnered significant attention from researchers in the field of spatio-temporal analysis, as it can generate substantial synthesized human mobility trajectories that enhance user privacy and alleviate data scarcity. However, existing trajectory generation methods often focus on improving trajectory generation quality from a singular perspective, lacking a comprehensive semantic understanding across various scales. Consequently, we are inspired to develop a HOlistic SEmantic Representation (HOSER) framework for navigational trajectory generation. Given an origin- and-destination (OD) pair and the starting time point of a latent trajectory, we first propose a Road Network Encoder to expand the receptive field of road- and zone-level semantics. Second, we design a Multi-Granularity Trajectory Encoder to integrate the spatio-temporal semantics of the generated trajectory at both the point and trajectory levels. Finally, we employ a Destination-Oriented Navigator to seamlessly integrate destination-oriented guidance. Extensive experiments on three real-world datasets demonstrate that HOSER outperforms state-of-the-art baselines by a significant margin. Moreover, the model’s performance in few-shot learning and zero-shot learning scenarios further verifies the effectiveness of our holistic semantic representation. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL 39

Cooperative Policy Agreement: Learning Diverse Policy for Of...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Yihe Zheng, Yuxuan Hu, Yue Chen, Kaixuan Zheng, Tongya Song, Jie Song, Mingli Liu, Shunyu Zhejiang University China Nanyang Technological University Singapore State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Big Graph Center Hangzhou City University China

ISBN: (纸本)157735897X

Offline Multi-Agent Reinforcement Learning (MARL) aims to learn optimal joint policies from pre-collected datasets without further interaction with the environment. Despite the encouraging results achieved so far, we identify the policy mismatch problem that arises from employing diverse offline MARL datasets, a highly important ingredient for cooperative generalization yet largely overlooked by existing literature. Specifically, in the case that offline datasets exhibit various optimal joint policies, policy mismatch often occurs when individual actions from different optimal joint actions are combined in a way that results in suboptimal joint actions. In this paper, we introduce a novel Cooperative Policy Agreement (CPA) method, that not only mitigates the policy mismatch problem but also learns to generate diverse joint policies. CPA firstly introduces an autoregressive decision-making mechanism among agents during offline training. This mechanism enables agents to access the actions previously taken by other agents, thereby facilitating effective joint policy matching. Moreover, diverse joint policies can be directly obtained through sequential action sampling from the autoregressive model. Then we further incorporate a policy agreement mechanism to convert these autoregressive joint policies into decentralized policies with a non-autoregressive form, while still ensuring the diversity of the generated policies. This mechanism guarantees that the proposed CPA adheres to the Centralized Training with Decentralized Execution (CTDE) constraint. Experiments conducted on various benchmarks demonstrate that CPA yields superior performance to state-of-the-art competitors. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TPIA: Towards Target-specific Prompt Injection Attack against Code-oriented Large Language Models

arXiv

引用

arXiv 2024年

作者： Yang, Yuchen Yao, Hongwei Yang, Bingrun He, Yiling Li, Yiming Zhang, Tianwei Qin, Zhan State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou310007 China Institute of Blockchain and Data Security Hangzhou310053 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Recently, code-oriented large language models (Code LLMs) have been widely and successfully exploited to simplify and facilitate programming. Unfortunately, a few pioneering works revealed that these Code LLMs are vulnerable to backdoor and adversarial attacks. The former poisons the training data or model parameters, hijacking the LLMs to generate malicious code snippets when encountering the trigger. The latter crafts malicious adversarial input codes to reduce the quality of the generated codes. In this paper, we reveal that both attacks have some inherent limitations: backdoor attacks rely on the adversary’s capability of controlling the model training process, which may not be practical;adversarial attacks struggle with fulfilling specific malicious purposes. To alleviate these problems, this paper presents a novel attack paradigm against Code LLMs, namely target-specific prompt injection attack (TPIA). TPIA generates non-functional perturbations containing the information of malicious instructions and inserts them into the victim’s code context by spreading them into potentially used dependencies (e.g., packages or RAG’s knowledge base). It induces the Code LLMs to generate attacker-specified malicious code snippets at the target location. In general, we compress the attacker-specified malicious objective into the perturbation by adversarial optimization based on greedy token search. We collect 13 representative malicious objectives to design 31 threat cases for three popular programming languages. We show that our TPIA can successfully attack three representative open-source Code LLMs (with an attack success rate of up to 97.9%) and two mainstream commercial Code LLM-integrated applications (with an attack success rate of over 90%) in all threat cases, using only a 12-token non-functional perturbation. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

PipeCo: Pipelining Cold Start of Deep Learning Inference Services on Serverless Platforms 25

PipeCo: Pipelining Cold Start of Deep Learning Inference Ser...

引用

Abstracts of the 2025 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems

作者： Jiaang Duan Shiyou Qian Hanwen Hu Dingyu Yang Jian Cao Guangtao Xue Shanghai Jiao Tong University Shanghai China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China

ISBN: (纸本)9798400715938

The fusion of serverless computing and deep learning (DL) has led to serverless inference, offering a promising approach for developing and deploying scalable and cost-efficient deep learning inference services (DLISs). However, the challenge of cold start presents a significant obstacle for DLISs, where DL model size greatly impacts latency. Existing studies mitigate cold starts by extending keep-alive times, which unfortunately leads to decreased resource utilization efficiency. To address this issue, we introduce PipeCo, a system designed to alleviate DLIS cold start. The core concept of PipeCo is to achieve the miniaturization and pipelining of DLIS cold start. Firstly, PipeCo utilizes a vertical partitioning approach to divide each DLIS into multiple slices, prewarming slices in a sequential and overlapping manner to decrease the overall cold-start latency. Secondly, PipeCo employs an attention-based prediction mechanism to estimate periodic patterns in requests and idle containers for scheduling slices. Thirdly, PipeCo incorporates a similarity-based container matcher for the reuse of idle containers. We implemented a prototype of PipeCo on the OpenFaaS platform and conducted extensive experiments using three real-world DLIS repositories. The results demonstrate that PipeCo effectively decreases end-to-end (E2E) latency by up to 62.67% on CPU and 58.81% on GPU clusters and reduces the overall resource usage by 65.31% compared to five state-of-the-art baselines.

关键词： cold start

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：