检索结果-内蒙古大学图书馆

LLM-MalDetect: A Large Language Model-Based Method for Android Malware Detection

IEEE Access 2025年 13卷 81347-81364页

作者： Feng, Ruirui Chen, Hui Wang, Shuo Karim, Md Monjurul Jiang, Qingshan Hebei University College of Mathematics and Information Science Baoding071002 China Chinese Academy of Sciences Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institute of Advanced Technology Shenzhen518055 China Shenzhen Polytechnic University School of Artificial Intelligence Shenzhen518055 China

Android malware poses a significant cybersecurity threat, enabling unauthorized data access, financial fraud, and device compromise. Although deep learning methods are widely used for malware detection, they often struggle with stability and adaptability in the face of evolving threats. While large language models (LLMs) have shown promise in this area, their application to Android malware detection remains underexplored, particularly with regard to optimizing the semantic relationships within Android application packages (APKs). To address this gap, we introduce LLM-MalDetect, a novel framework that improves LLM-based APK analysis by explicitly modeling semantic dependencies and leveraging structured prompt engineering for optimized detection. Our approach formalizes LLM adaptation through a robust string-based feature extraction method and a tailored fine-tuning strategy to enhance precision. Evaluations on benchmark datasets demonstrate that LLM-MalDetect achieves up to 98.97% accuracy, outperforms existing methods in terms of robustness, and enables real-time analysis. © 2013 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Pre-training, Fine-tuning and Re-ranking: A Three-Stage Framework for Legal Question Answering

Pre-training, Fine-tuning and Re-ranking: A Three-Stage Fram...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shiwen Ni Hao Cheng Min Yang Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology CAS Shenzhen University of Advanced Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Legal question answering (QA) has attracted increasing attention from people seeking legal advice, which aims to retrieve the most applicable answers from a large-scale database of question-answer pairs. Previous methods mainly use a dual-encoder architecture to learn dense representations of both questions and answers. However, these methods could suffer from lacking domain knowledge and sufficient labeled training data. In this paper, we propose a three-stage (pre-training, fine-tuning and re-ranking) framework for legal QA (called PFR-LQA), which promotes the fine-grained text representation learning and boosts the performance of dense retrieval with the dual-encoder architecture. Concretely, we first conduct domain-specific pre-training on legal questions and answers through a self-supervised training objective, allowing the pre-trained model to be adapted to the legal domain. Then, we perform task-specific fine-tuning of the dual-encoder on legal question-answer pairs by using the supervised learning objective, leading to a high-quality dual-encoder for the specific downstream QA task. Finally, we employ a contextual re-ranking objective to further refine the output representations of questions produced by the document encoder, which uses contextual similarity to increase the discrepancy between the anchor and hard negative samples for better question re-ranking. We conduct extensive experiments on a manually annotated legal QA dataset. Experimental results show that our PFR-LQA method achieves better performance than the strong competitors for legal question answering.

关键词： Representation learning Training Law databases Supervised learning Training data Signal processing Question answering (information retrieval) Speech processing Standards

来源：评论

学校读者我要写书评

暂无评论

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations 31

CPsyExam: A Chinese Benchmark for Evaluating Psychology usin...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhao, Jiahao Zhu, Jingwei Tan, Minghuan Yang, Min Li, Renhao Yang, Di Zhang, Chenhao Ye, Guancheng Li, Chengming Hu, Xiping Wong, Derek F. Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shenzhen University of Advanced Technology China Jilin University China University of Science and Technology of China China University of Macau China Huazhong University of Science and Technology China South China University of Technology China Shenzhen MSU-BIT University China

ISBN: (纸本)9798891761964

In this paper, we introduce a novel psychological benchmark, CPsyExam, constructed from questions sourced from Chinese examination systems. CPsyExam is designed to prioritize psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios. We collect 22k questions from 39 psychology-related subjects across four Chinese examination systems. From the pool of 22k questions, we utilize 4k to create the benchmark that offers balanced coverage of subjects and incorporates a diverse range of case analysis techniques. Furthermore, we evaluate a range of existing large language models (LLMs), spanning from open-sourced to proprietary models. Our experiments and analysis demonstrate that CPsyExam serves as an effective benchmark for enhancing the understanding of psychology within LLMs and enables the comparison of LLMs across various granularities. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking

arXiv

引用

arXiv 2025年

作者： Lee, Sunbowen Ni, Shiwen Wei, Chi Li, Shuaimin Fan, Liyang Argha, Ahmadreza Alinejad-Rokny, Hamid Xu, Ruifeng Gong, Yicheng Yang, Min Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen University of Advanced Technology China WUST United States HITSZ China School of Biomedical Engineering UNSW Sydney Australia

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model’s internal parameters, a phenomenon known as black-box jailbreak. Existing heuristic black-box attack methods, such as genetic algorithms, suffer from limited effectiveness due to their inherent randomness, while recent reinforcement learning (RL) based methods often lack robust and informative reward signals. To address these challenges, we propose a novel black-box jailbreak method leveraging RL, which optimizes prompt generation by analyzing the embedding proximity between benign and malicious prompts. This approach ensures that the rewritten prompts closely align with the intent of the original prompts while enhancing the attack’s effectiveness. Furthermore, we introduce a comprehensive jailbreak evaluation framework incorporating keywords, intent matching, and answer validation to provide a more rigorous and holistic assessment of jailbreak success. Experimental results show the superiority of our approach, achieving state-of-the-art (SOTA) performance on several prominent open and closed-source LLMs, including Qwen2.5-7B-Instruct, Llama3.1-8B-Instruct, and GPT-4o-0806. Our method sets a new benchmark in jailbreak attack effectiveness, highlighting potential vulnerabilities in LLMs. The codebase for this work is available at https://***/Aegis1863/xJailbreak. Copyright © 2025, The Authors. 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

AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling

arXiv

引用

arXiv 2025年

作者： Xu, Ancheng Yang, Di Li, Renhao Zhu, Jingwei Tan, Minghuan Yang, Min Qiu, Wanxin Ma, Mingchen Wu, Haihong Li, Bingyu Sha, Feng Li, Chengming Hu, Xiping Qu, Qiang Wong, Derek F. Xu, Ruifeng Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Science and Technology of China China University of Macau China Shenzhen University China Shenzhen MSU-BIT University China Harbin Institute of Technology Shenzhen China

Traditional in-person psychological counseling remains primarily niche, often chosen by individuals with psychological issues, while online automated counseling offers a potential solution for those hesitant to seek help due to feelings of shame. Cognitive Behavioral Therapy (CBT) is an essential and widely used approach in psychological counseling. The advent of large language models (LLMs) and agent technology enables automatic CBT diagnosis and treatment. However, current LLM-based CBT systems use agents with a fixed structure, limiting their self-optimization capabilities, or providing hollow, unhelpful suggestions due to redundant response patterns. In this work, we utilize Quora-like1 and YiXinLi2 single-round consultation models to build a general agent framework that generates high-quality responses for single-turn psychological consultation scenarios. We use a bilingual dataset to evaluate the quality of single-response consultations generated by each framework. Then, we incorporate dynamic routing and supervisory mechanisms inspired by real psychological counseling to construct a CBT-oriented autonomous multi-agent framework, demonstrating its general applicability. Experimental results indicate that AutoCBT can provide higher-quality automated psychological counseling services. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Personality Traits on LLM Bias and Toxicity

arXiv

引用

arXiv 2025年

作者： Wang, Shuo Li, Renhao Chen, Xi Wong, Derek F. Yuan, Yulin Yang, Min NLP2CT Lab Department of Computer and Information Science University of Macau China Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Linguistics and Multilingual Studies Nanyang Technological University Singapore Department of Chinese Language and Literature University of Macau China

With the different roles that AI is expected to play in human life, imbuing large language models (LLMs) with different personalities has attracted increasing research interests. While the "personification" enhances human experiences of interactivity and adaptability of LLMs, it gives rise to critical concerns about content safety, particularly regarding bias, sentiment and toxicity of LLM generation. This study explores how assigning different personality traits to LLMs affects the toxicity and biases of their outputs. Leveraging the widely accepted HEXACO personality framework developed in social psychology, we design experimentally sound prompts to test three LLMs’ performance on three toxic and bias benchmarks. The findings demonstrate the sensitivity of all three models to HEXACO personality traits and, more importantly, a consistent variation in the biases, negative sentiment and toxicity of their output. In particular, adjusting the levels of several personality traits can effectively reduce bias and toxicity in model performance, similar to humans’ correlations between personality traits and toxic behaviors. The findings highlight the additional need to examine content safety besides the efficiency of training or fine-tuning methods for LLM personification. They also suggest a potential for the adjustment of personalities to be a simple and low-cost method to conduct controlled text generation. © 2025, CC BY.

关键词： Social psychology

来源：评论

学校读者我要写书评

暂无评论

Relative manifold based semi-supervised dimensionality reduction

引用

Frontiers of Computer Science 2014年第6期8卷 923-932页

作者： Xianfa CAI Guihua WEN Jia WEI Zhiwen YU School of Medical Information Engineering Guangdong Pharmaceutical University Guangzhou 510006 China School of Computer Science and Engineering South China University of Technology Guangzhou 510006 China Shenzhen Key Laboratory of High Performance Data Mining Shenzhen 518055 China

A well-designed graph plays a fundamental role in graph-based semi-supervised learning; however, the topological structure of a constructed neighborhood is unstable in most current approaches, since they are very sensitive to the high dimensional, sparse and noisy data. This generally leads to dramatic performance degradation. To deal with this issue, we developed a relative manifold based semisupervised dimensionality reduction （RMSSDR） approach by utilizing the relative manifold to construct a better neighborhood graph with fewer short-circuit edges. Based on the relative cognitive law and manifold distance, a relative transformation is used to construct the relative space and the relative manifold. A relative transformation can improve the ability to distinguish between data points and reduce the impact of noise such that it may be more intuitive, and the relative manifold can more truly reflect the manifold structure since data sets commonly exist in a nonlinear structure. Specifically, RMSSDR makes full use of pairwise constraints that can define the edge weights of the neighborhood graph by minimizing the local reconstruction error and can preserve the global and local geometric structures of the data set. The experimental results on face data sets demonstrate that RMSSDR is better than the current state of the art comparing methods in both performance of classification and robustness.

关键词： cognitive law relative transformation relative manifold local reconstruction semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A novel splice site prediction method using support vector machine

引用

Journal of Computational Information Systems 2013年第20期9卷 8053-8060页

作者： Wei, Dan Zhang, Huiling Wei, Yanjie Jiang, Qingshan Cognitive Science Department and Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen University Xiamen 361005 China Shenzhen Key Lab. for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China

We present a novel classification method for splice sites prediction using support vector machine (SVM). The method first represents input sequences by sequence-based features, including the information of the distribution of tri-nucleotides and the conserved features surrounding the splice sites characterized by Markov model. An F-score based feature selection method is then used to select informative features to improve the performance. Finally, SVM is employed to classify the splice sites with the selected features. Experimental results show that this method improves splice site prediction accuracy and performs better than the existing methods such as MM1-SVM, Reduced MM1-SVM and some other methods. © 2013 Binary Information Press.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Graph algorithms: parallelization and scalability

引用

Science China(Information Sciences) 2020年第10期63卷 234-254页

作者： Wenfei FAN Kun HE Qian LI Yue WANG School of Informatics University of Edinburgh Shenzhen Institute of Computing Sciences Shenzhen University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Guangdong Province Key Laboratory of Popular High Performance Computers Shenzhen University

For computations on large-scale graphs, one often resorts to parallel algorithms. However, parallel algorithms are difficult to write, debug and analyze. Worse still, it is difficult to make algorithms parallelly scalable, such that the more machines are used, the faster the algorithms run. Indeed, it is not yet known whether any PTIME computational problems admit parallelly scalable algorithms on shared-nothing *** it possible to parallelize sequential graph algorithms and guarantee convergence at the correct results as long as the sequential algorithms are correct? Moreover, does a PTIME parallelly scalable problem exist on shared-nothing systems? This position paper answers both questions in the affirmative.

关键词： parallelization parallel scalability PTIME problems graph algorithms shared-nothing systems

来源：评论

学校读者我要写书评

暂无评论

Research on vulnerability detection for software based on taint analysis

Research on vulnerability detection for software based on ta...

引用

2013 International Conference on Precision Mechanical Instruments and Measurement Technology, ICPMIMT 2013

作者： Liang, Bei Hai Qu, Bin Bin Jiang, Sheng Ye, Chu Tian School of Compute Science Huazhong University of Science and Technology Wuhan 430074 China Shenzhen Key Laboratory of High Performance Data Mining Shenzhen 518055 China

At present, Cross Site Scripting (XSS) vulnerability exists in most web sites. The main reason is the lack of effective validation and filtering mechanisms for user input data from web request. This paper explores vulnerability detection method which based on taint dependence analysis and implements a prototype system for Java Web program. We treat all user input as tainted data, and track the flow of Web applications, then we judge whether it will trigger an attack or not. The taint dependent analysis algorithm mentioned in this paper is used to construct the taint dependency graph. Next the value representation method of the string tainted object based on finite state automata is discussed. Finally, we propose the vulnerability detection method for the program. The experiment result shows that the prototype system can detect reflection cross-site scripting vulnerability well in those programs which don't have effective treatment for the user input data. © 2013 Trans Tech Publications Ltd, Switzerland.

关键词： Input output programs

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：