检索结果-内蒙古大学图书馆

9th IEEE International Conference on data Science in Cyberspace, DSC 2024

作者： Xiang, Hui Wu, Yifan Wang, Xuebin Shi, Jinqiao Zhao, Can Zhao, Jiapeng Beijing University of Posts and Telecommunications School of Cyberspace Security Beijing China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China Chinese Academy of Sciences Institute of Information Engineering Beijing China

ISBN: (纸本)9798350391367

Frequent data breaches have attracted people's attention. The dark web forums have become the crucial platform for data breach transactions. While some forums are well-organized with distinct sections, such as a dedicated area for leaks where most threads are related to data breaches, others lack clear segmentation, like Fear Forum. Hackers conduct a variety of discussions there so it is filled with tons of non-data breach information and building a data breach dataset for a classifier requires huge human resources. The content of these threads is diverse and complex, spanning various fields, and containing specific terminology in the dark web. Identifying data breach threads in these forums is extremely challenging for the model. With the influx of new threads every day the static model trained on old data may not perform well when processing new data, which also brings serious difficulty to identification. To address these challenges, we first design Prompt-based Active Learning (PAL) to guide the model to identify through prompts and select high-quality samples for annotation. Then we propose a system that combines PAL and DarkBERT. Our system can not only greatly reduce annotation costs but also continuously learn and update itself with the new informative data selected by PAL. Through rich experiments on a data breach dataset, we demonstrate that our system effectively identifies breach threads and PAL significantly outperforms other baselines. We also search for the optimal prompt templates to improve system performance. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting

arXiv

引用

arXiv 2024年

作者： Shang, Zongjiang Chen, Ling Wu, Binqing Cui, Dongliang State Key Laboratory of Blockchain and Data Security College of Computer Science and Technology Zhejiang University China

Although transformer-based methods have achieved great success in multi-scale temporal pattern interaction modeling, two key challenges limit their further development: (1) Individual time points contain less semantic information, and leveraging attention to model pair-wise interactions may cause the information utilization bottleneck. (2) Multiple inherent temporal variations (e.g., rising, falling, and fluctuating) entangled in temporal patterns. To this end, we propose Adaptive Multi-Scale Hypergraph Transformer (Ada-MSHyper) for time series forecasting. Specifically, an adaptive hypergraph learning module is designed to provide foundations for modeling group-wise interactions, then a multi-scale interaction module is introduced to promote more comprehensive pattern interactions at different scales. In addition, a node and hyperedge constraint mechanism is introduced to cluster nodes with similar semantic information and differentiate the temporal variations within each scales. Extensive experiments on 11 real-world datasets demonstrate that Ada-MSHyper achieves state-of-the-art performance, reducing prediction errors by an average of 4.56%, 10.38%, and 4.97% in MSE for long-range, short-range, and ultra-long-range time series forecasting, respectively. Code is available at https://***/shangzongjiang/Ada-MSHyper. Copyright © 2024, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution 39

Advancing Loss Functions in Recommender Systems: A Comparati...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Shengjia Chen, Jiawei Li, Changdong Zhou, Sheng Shi, Qihao Feng, Yan Chen, Chun Wang, Can State Key Laboratory of Blockchain and Data Security Zhejiang University China College of Computer Science Zhejiang University China Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security China

ISBN: (纸本)157735897X

Loss functions play a pivotal role in optimizing recommendation models. Among various loss functions, Softmax Loss (SL) and Cosine Contrastive Loss (CCL) are particularly effective. Their theoretical connections and differences warrant in-depth exploration. This work conducts comprehensive analyses of these losses, yielding significant insights: 1) Common strengths - both can be viewed as augmentations of traditional losses with Distributional Robust Optimization (DRO), enhancing robustness to distributional shifts;2) Respective limitations - stemming from their use of different distribution distance metrics in DRO optimization, SL exhibits high sensitivity to false negative instances, whereas CCL suffers from low data utilization. To address these limitations, this work proposes a new loss function, DrRL, which generalizes SL and CCL by leveraging Rényi-divergence in DRO optimization. DrRL incorporates the advantageous structures of both SL and CCL, and can be demonstrated to effectively mitigate their limitations. Extensive experiments have been conducted to validate the superiority of DrRL on both recommendation accuracy and robustness. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BSL: Understanding and Improving Softmax Loss for Recommendation 40

BSL: Understanding and Improving Softmax Loss for Recommenda...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Wu, Junkang Chen, Jiawei Wu, Jiancan Shi, Wentao Zhang, Jizhi Wang, Xiang University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition Hefei China Zhejiang Unversity The State Key Laboratory of Blockchain and Data Security China Institute of Artificial Intelligence Institute of Dataspace Hefei Comprehensive National Science Center. China

ISBN: (纸本)9798350317152

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL) stands out for not only achieving remarkable accuracy but also better robustness and fairness. Nevertheless, the current literature lacks a comprehensive explanation for the efficacy of SL. Toward addressing this research gap, we conduct theoretical analyses on SL and uncover three insights: 1) Optimizing SL is equivalent to performing Distributionally Robust Optimization (DRO) on the negative data, thereby learning against perturbations on the negative distribution and yielding robustness to noisy negatives. 2) Comparing with other loss functions, SL implicitly penalizes the prediction variance, resulting in a smaller gap between predicted values and and thus producing fairer results. Building on these insights, we further propose a novel loss function Bilateral SoftMax Loss (BSL) that extends the advantage of SL to both positive and negative sides. BSL augments SL by applying the same Log-Expectation-Exp structure to positive examples as is used for negatives, making the model robust to the noisy positives as well. Remarkably, BSL is simple and easy-to-implement -requiring just one additional line of code compared to SL. Experiments on four real-world datasets and three representative backbones demonstrate the effectiveness of our proposal. The code is available at https://***/junkangwu/BSL. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Shapley Value in data Analytics

arXiv

引用

arXiv 2024年

作者： Lin, Hong Wan, Shixin Xie, Zhongle Chen, Ke Zhang, Meihui Shou, Lidan Chen, Gang State Key Laboratory of Blockchain and Data Security Zhejiang University China Beijing Institute of Technology China

Over the recent years, Shapley value (SV), a solution concept from cooperative game theory, has found numerous applications in data analytics (DA). This paper provides the first comprehensive study of SV used throughout the DA workflow, which involves three main steps: data fabrication, data exploration, and result reporting. We summarize existing versatile forms of SV used in these steps by a unified definition and clarify the essential functionalities that SV can provide for data scientists. We categorize the arts in this field based on the technical challenges they tackled, which include computation efficiency, approximation error, privacy preservation, and appropriate interpretations. We discuss these challenges and analyze the corresponding solutions. We also implement SVBench, the first open-sourced benchmark for developing SV applications, and conduct experiments on six DA tasks to validate our analysis and discussions. Based on the qualitative and quantitative results, we identify the limitations of current efforts for applying SV to DA and highlight the directions of future research and engineering. © 2024, CC BY.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach

arXiv

引用

arXiv 2024年

作者： Chen, Qian Chen, Ling State Key Laboratory of Blockchain and Data Security College of Computer Science and Technology Zhejiang University China

Temporal Knowledge Graph (TKG) representation learning aims to map temporal evolving entities and relations to embedded representations in a continuous low-dimensional vector space. However, existing approaches cannot capture the temporal evolution of high-order correlations in TKGs. To this end, we propose a Deep Evolutionary Clustering jointed temporal knowledge graph Representation Learning approach (DECRL). Specifically, a deep evolutionary clustering module is proposed to capture the temporal evolution of high-order correlations among entities. Furthermore, a cluster-aware unsupervised alignment mechanism is introduced to ensure the precise one-to-one alignment of soft overlapping clusters across timestamps, thereby maintaining the temporal smoothness of clusters. In addition, an implicit correlation encoder is introduced to capture latent correlations between any pair of clusters under the guidance of a global graph. Extensive experiments on seven real-world datasets demonstrate that DECRL achieves the state-of-the-art performances, outperforming the best baseline by an average of 9.53%, 12.98%, 10.42%, and 14.68% in MRR, Hits@1, Hits@3, and Hits@10, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Training data Provenance Verification: Did Your Model Use Synthetic data from My Generative Model for Training?

arXiv

引用

arXiv 2025年

作者： Xie, Yuechen Song, Jie Wang, Huiqiong Song, Mingli Zhejiang University China Ningbo Innovation Center Zhejiang University China State Key Laboratory of Blockchain and Security Zhejiang University China Institute of Blockchain and Data Security China

High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated by these generative models to train models for specific tasks without permission, when lacking real data resources especially. Protecting these generative models is crucial for the well-being of their owners. In this work, we propose the first method to this important yet unresolved issue, called Training data Provenance Verification (TrainProVe). The rationale behind TrainProVe is grounded in the principle of generalization error bound, which suggests that, for two models with the same task, if the distance between their training data distributions is smaller, their generalization ability will be closer. We validate the efficacy of TrainProVe across four text-to-image models (Stable Diffusion v1.4, latent consistency model, PixArt-α, and Stable Cascade). The results show that TrainProVe achieves a verification accuracy of over 99% in determining the provenance of suspicious model training data, surpassing all previous methods. Code is available at https://***/xieyc99/TrainProVe. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks 38

Model LEGO: Creating Models Like Disassembling and Assemblin...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Jiacong Gao, Jing Ye, Jingwen Gao, Yang Wang, Xingen Feng, Zunlei Song, Mingli College of Computer Science and Technology Zhejiang University China Robotics Institute School of Computer Science Carnegie Mellon University United States Electrical and Computer Engineering National University of Singapore Singapore School of Software Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Bangsheng Technology Co. Ltd. China

With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start from the classic convolutional neural network (CNN) and explore a paradigm that does not require training to obtain new models. Similar to the birth of CNN inspired by receptive fields in the biological visual system, we draw inspiration from the information subsystem pathways in the biological visual system and propose Model Disassembling and Assembling (MDA). During model disassembling, we introduce the concept of relative contribution and propose a component locating technique to extract task-aware components from trained CNN classifiers. For model assembling, we present the alignment padding strategy and parameter scaling strategy to construct a new model tailored for a specific task, utilizing the disassembled task-aware components. The entire process is akin to playing with LEGO bricks, enabling arbitrary assembly of new models, and providing a novel perspective for model creation and reuse. Extensive experiments showcase that task-aware components disassembled from CNN classifiers or new models assembled using these components closely match or even surpass the performance of the baseline, demonstrating its promising results for model reuse. Furthermore, MDA exhibits diverse potential applications, with comprehensive experiments exploring model decision route analysis, model compression, knowledge distillation, and more. For more information, please visit https://***/. © 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

Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study

arXiv

引用

arXiv 2025年

作者： Wang, You Pradel, Michael Liu, Zhongxin The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China University of Stuttgart Stuttgart Germany

Automated issue solving aims to resolve real-world issues in software repositories. The most popular benchmarks for automated issue solving are SWE-bench and its human-filtered subset SWE-bench Verified, which are widely used to evaluate foundation models and software engineering agents. These benchmarks leverage testing to validate generated patches. However, because testing is rarely exhaustive, a patch may pass the tests but nevertheless fail to match the developers’ expectations. Unfortunately, it is currently unclear to what extent evaluations performed with SWE-bench suffer from such plausible but incorrect patches. This paper presents an in-depth empirical study of the correctness of plausible patches generated by three state-of-the-art issue-solving tools (CodeStory, LearnByInteract, and OpenHands) evaluated on SWE-bench Verified. We extensively test and inspect generated patches, and compare them against human-written ground truth patches. The core of our methodology is a novel technique PatchDiff for differential patch testing, which automatically exposes behavioral discrepancies between two patches. Our findings reveal critical weaknesses in SWE-bench’s patch validation mechanism, which causes 7.8% of all patches to count as "correct" while failing the developer-written test suite. Moreover, our novel automated technique reveals that even more (29.6%) plausible patches induce different behavior than the ground truth patches. These behavioral differences are often due to similar, but divergent implementations (46.8%) and due to generated patches that adapt more behavior than the ground truth patches (27.3%). Our manual inspection shows that 28.6% of behaviorally divergent patches are certainly incorrect. Combined, the different weaknesses lead to an inflation of reported resolution rates by 6.2 absolute percent points. Our findings are a call to arms for more robust and reliable evaluation of issue-solving tools. We envision our automated differential patc

关键词： Software agents

来源：评论

学校读者我要写书评

暂无评论

APIBeh: Learning Behavior Inclination of APIs for Malware Classification

APIBeh: Learning Behavior Inclination of APIs for Malware Cl...

引用

International Symposium on Software Reliability Engineering (ISSRE)

作者： Lei Cui Yiran Zhu Junnan Yin Zhiyu Hao Wei Wang Peng Liu Ziqi Yang Xiaochun Yun Zhongguancun Laboratory The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security School of Computer Science and Engineering Guangxi Normal University

ISBN: (数字)9798350353884

ISBN: (纸本)9798350353891

Malware classification involves categorizing mal-ware samples based on their characteristics. While deep learning techniques applied to malware execution traces, mainly API calls, have shown potential in this field, they still perform poorly. This is primarily because they treat all APIs equally and train classifiers directly on native APIs, which inadequately capture the under-lying family-related semantics. In this paper, we first investigate the behaviors of multiple malware families and observe that different families exhibit divergent behaviors, with each family consistently favoring certain behaviors over time. Motivated by this, we propose APIBeh, a new embedding method designed to enhance malware classification. APIBeh first utilizes Benignity Degree Algorithm to identify and exclude insignificant, likely benign APIs from sequences. Then, it introduces the concept of Behavior Inclination, which quantifies the association between an API and malicious behaviors, facilitating high-level behavior encoding for each API. This Behavior Inclination embedding is then concatenated with raw embedding to represent an API, and fed into a DL model for classifier training. Experimental results show that APIBeh outperforms existing embedding methods in classification performance, e.g., 3.18% boost in weighted f1-score over a recent study using word2vec. In addition, it offers robustness to concept drift and adversarial attacks.

关键词： Training Deep learning Concept drift Semantics Focusing Syntactics Malware Robustness Encoding Software reliability

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：