检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Yang, Kang Cai, Lizhi Wu, Jianhua Liu, Zhenyu Zhang, Meng Shanghai Key Laboratory of Computer Software Testing Evaluating Shanghai201112 China Shanghai Development Center of Computer Software Technology Shanghai201112 China

With the significant increase of Android malware, the application privacy data leakage incidents occur frequently, which poses a great threat to user property and information security. However, the new malware has the characteristics of high evolution rate and diverse variants, leading to the fact that the current malware detection methods still have three key problems: (1) Difficulty in acquiring Android sample structural features;(2) Weakly in representing malware behavior structure;(3) Poor robustness of the detection model. To address the above limitations, we proposes a new malware detection framework MPRLDroid with reinforcement learning. First of all, the MPRLDroid model extracts the Android application structural features and constructs the heterogeneous information network data based on the semantic call structure between APP, API and permission. Subsequently, the model uses reinforcement learning algorithm to adaptively generate meta-paths for each sample and incorporates graph attention network to effectivelyrepresentation the graph of node. Finally, the low-dimensional graph node vector data brought into the downstream detection task for classification, where the performance change of the classification result is used as a reward function for reinforcement learning. The experimental results show that the performance of the MPRLDRroid model combined with reinforcement learning outperforms the baseline models, and the robustness of the detection model is also better than other models. © 2023, The Authors. All rights reserved.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping

arXiv

引用

arXiv 2024年

作者： Ji, Yuzhou Zhu, He Tang, Junshu Liu, Wuyi Zhang, Zhizhong Tan, Xin Xie, Yuan East China Normal University Shanghai China Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing China

The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications. However, it is a challenging task to achieve high quality, efficiency and zero-shot ability at the same time with semantics in radiance fields. In this work, we present FastLGS, an approach that supports real-time open-vocabulary query within 3D Gaussian Splatting (3DGS) under high resolution. We propose the semantic feature grid to save multi-view CLIP features which are extracted based on Segment Anything Model (SAM) masks, and map the grids to low dimensional features for semantic field training through 3DGS. Once trained, we can restore pixel-aligned CLIP embeddings through feature grids from rendered features for open-vocabulary queries. Comparisons with other state-of-the-art methods prove that FastLGS can achieve the first place performance concerning both speed and accuracy, where FastLGS is 98 × faster than LERF, 4 × faster than LangSplat and 2.5 × faster than LEGaussians. Meanwhile, experiments show that FastLGS is adaptive and compatible with many downstream tasks, such as 3D segmentation and 3D object inpainting, which can be easily applied to other 3D manipulation systems. © 2024, CC BY-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RGA-Reid: Neural Architecture Search Based on Relation-Aware Global Attention for Person Re-Identification

RGA-Reid: Neural Architecture Search Based on Relation-Aware...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Shijie Chen Shengbo Chen Zhou Lei School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai China

With the continuous development of deep learning, reid has been continually improved. However, the network backbones of reid are mostly manually designed. This paper proposes RGA-Reid based on auto-reid. NASBR-Reid obtains the network backbone through neural architecture search. It replaces the part-base module in the auto-reid search algorithm with the RGA module, which effectively integrates global relationships to enhance attention training between different parts. Experimental results demonstrate that RGA-Reid can retrieve superior network backbones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FAS-reid: Fair Architecture Search for Person Re-IDentification

FAS-reid: Fair Architecture Search for Person Re-IDentificat...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Shengbo Chen Shijie Chen Zhou Lei School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai China

The development of deep learning has driven the development of ReID, and more and more excellent methods have been proposed, but most of these are artificially designed network backbones. Automation is a trend in the development of deep learning. This paper propose FAS-ReID(Fair Architecture Search for Person Re-IDentification), which can automatically design and generate a neural network backbone for ReID. This paper compare operation selection to competition, and inject noise to make the competition fairer, while making the architecture of automated search More adaptable to ReID We use TriHard loss to improve the feature extraction ability. Our experiments show that the backbone searched by FAS-ReID is better and reduces the search time. Meanwhile, as for the problem of performance collapse caused by skip-connection enrichment in the search process, FAS-Reid does not use the early stop strategy to avoid performance loss like other solutions, which is also the reason why our method is more reliable and robust.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Extractive and Abstractive Models for Code Comment Generation

Integrating Extractive and Abstractive Models for Code Comme...

引用

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

作者： Weisong Sun Yuling Hu Yingfei Xu Yuchen Chen Chunrong Fang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

Code comments play an essential role in aiding developers understand and maintain source code. Current code comment generation techniques can be classified into categories: extractive methods and abstractive methods. Extractive methods use text retrieval techniques to extract important code tokens to constitute comments. Such comments contain important factual details articulated explicitly in code tokens, but are poor in naturalness. Abstractive methods usually regard code comment generation as a neural machine translation task. By leveraging powerful deep learning-based language models, abstractive methods can generate comments that resemble human writing. However, compared with natural language, programming language code is more complex. Comments generated by abstractive methods often leave out important factual details. In this paper, we propose a novel method for code comment generation by integrating extractive and abstractive models. Our extractive model is built on the Latent Semantic Analysis (LSA) model, effectively extracting important factual details in code snippets. Meanwhile, our abstractive model is built on a deep learning-based encoder-decoder model, enabling it to generate concise and human-written-like comments. We evaluate the effectiveness of our method, called ICS, by conducting extensive experiments on the CodeSearchNet dataset involving six programming languages. The results demonstrate that ICS outperforms state-of-the-art techniques in three widely used metrics: BLEU, METEOR, and ROUGE-L. Moreover, the outcomes of the human evaluation indicate that the comments generated by ICS exhibit superior naturalness and informativeness, and closely align with the provided code snippets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contrastive Pseudo Learning for Open-World DeepFake Attribution

Contrastive Pseudo Learning for Open-World DeepFake Attribut...

引用

International Conference on computer Vision (ICCV)

作者： Zhimin Sun Shen Chen Taiping Yao Bangjie Yin Ran Yi Shouhong Ding Lizhuang Ma Shanghai Jiao Tong University Tencent YouTu Lab Shanghai Key Laboratory of Computer Software Testing & Evaluating

The challenge in sourcing attribution for forgery faces has gained widespread attention due to the rapid development of generative techniques. While many recent works have taken essential steps on GAN-generated faces, more threatening attacks related to identity swapping or expression transferring are still overlooked. And the forgery traces hidden in unknown attacks from the open-world unlabeled faces still remain under-explored. To push the related frontier research, we introduce a new benchmark called Open-World DeepFake Attribution (OW-DFA), which aims to evaluate attribution performance against various types of fake faces under open-world scenarios. Meanwhile, we propose a novel framework named Contrastive Pseudo Learning (CPL) for the OW-DFA task through 1) introducing a Global-Local Voting module to guide the feature alignment of forged faces with different manipulated regions, 2) designing a Confidence-based Soft Pseudo-label strategy to mitigate the pseudo-noise caused by similar methods in unlabeled set. In addition, we extend the CPL framework with a multi-stage paradigm that leverages pre-train technique and iterative learning to further enhance traceability performance. Extensive experiments verify the superiority of our proposed method on the OW-DFA and also demonstrate the interpretability of deepfake attribution task and its impact on improving the security of deepfake detection area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Hallucination and Robustness for Large Language Models

Evaluation of Hallucination and Robustness for Large Languag...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Rui Hu Junhao Zhong Minjie Ding Zeyu Ma Mingang Chen Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer Software Technology Shanghai China Shanghai AI Industry Association Shanghai China

As large language models (LLMs) rapidly advance, rigorous testing and evaluation of these models grows increasingly crucial. To address this need, we have developed three types of questions: Chinese contextual, English contextual, and language context-independent. testing in both Chinese and English probes the LLMs' hallucination tendencies. We investigate the impact of language on hallucinations from two perspectives: the type of language used in the input prompt and the cultural context underlying the prompt's content. Additionally, 52 multi-domain single-choice questions from C-EVAL are presented in original and randomized order to assess robustness to perturbations. Among the five LLMs, the tests demonstrate GPT -4 has the strongest anti-hallucination and robustness capabilities, answering with greater accuracy, consistency, and reliability. ChatGLM ranks second and outperforms GPT -4 on Chinese context-dependent questions. Emergent testing phenomena are analyzed from the user's perspective. Hallucinated responses are categorized and potential causal factors leading to hallucination and fragility are examined. Based on these findings, viable avenues for improvement are proposed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InsightCube: Accelerating Interactive Insight Discovery in Exploratory Data Analysis

InsightCube: Accelerating Interactive Insight Discovery in E...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Hanbing Zhang Yinan Jing Wei Zhang Zhenying He Kai Zhang X. Sean Wang Zhenqiang Chen Changchun Zhang School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Transwarp Technology(Shanghai) Co. Ltd Shanghai China

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Exploratory data analysis (EDA) is usually human-in-the-loop and time tedious since identifying insights that show interesting characteristics and trends in data is laborious. Insight discovery helps users gain structured knowledge when understanding the dataset by categorizing interesting characteristics and trends into commonnesses and exceptions. However, existing insight discovery methods cannot interact with users when discovering insights. More importantly, the efficiency of insight discovery for these methods is low. In this paper, we propose a framework that supports and accelerates interactive insight discovery. We first divide the dataset into multiple subsets, and precompute the pattern snippets that include the distribution characteristics of subsets. Considering efficiency, we only pre-compute for subsets that cannot be further split. Then we design a novel cube structure, called InsightCube, to store precomputed pattern snippets. In order to accelerate insight discovery, we reuse the precomputed pattern snippets stored in InsightCube to infer the pattern of subsets that cannot be split. Furthermore, during insight discovery, we propose pruning strategies to accelerate the pattern inference for subsets that can be split. Experimental results on real-world datasets show that InsightCube improves the insight discovery efficiency by up to $2.5 \times$ compared to the state-of-the-art insight discovery method.

关键词： Data analysis Big Data Market research Human in the loop Optimization

来源：评论

学校读者我要写书评

暂无评论

Object Oriented BDD and Executable Human-Language Module Specification 26

Object Oriented BDD and Executable Human-Language Module Spe...

引用

26th ACIS International Winter Conference on software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Winter 2023

作者： Lee, Eric Gong, Jiayu Cao, Qinghong Intelligent Technology Co. Ltd. Shanghai China Shanghai Key Laboratory of Computer Software Testing & Evaluation Shanghai Development Center of Computer Software Technology Shanghai China System Operation Department Shanghai Stock Exchange Shanghai China

ISBN: (纸本)9798350345865

This paper presents an approach to software development which uses a generative AI Model as compiler to translate human language requirements into high-level programming language. We propose an executable human-language module specification and a tool to support it, which has been used successfully for human-language UI test automation. We anticipate further development of this approach to enable complex software to be programmed in human language, allowing for more intuitive and efficient software development. © 2023 IEEE.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

An Approach to Optimize Symbolic Execution in Ethereum Smart Contracts

An Approach to Optimize Symbolic Execution in Ethereum Smart...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Yi Liu Lizhi Cai Chenchen Chai Yuan Ma School of Information Science and Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory of Computer Software Testing & Evaluating Shanghai Development Center of Computer Software Technology Shanghai China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

As the application of smart contracts in blockchain technology becomes increasingly widespread, their security issues have emerged as a focal point of both research and practice. Although symbolic execution technology has been extensively applied for the detection of security vulnerabilities in smart contracts, its limitations in terms of execution efficiency and code coverage remain significant. In response to these challenges, this study introduces an innovative method named HoneyToken-DetectorRev, which optimizes traditional symbolic execution through program slicing technology, aiming to enhance the efficiency and effectiveness of smart contract security detection. By selecting ten smart contracts from the Ethereum platform, which vary in business logic and complexity, we conducted an empirical analysis of HoneyToken-DetectorRev. The experimental results demonstrate that this method significantly improves the efficiency of smart contract detection without sacrificing precision. This research not only provides an effective technical approach for the security detection of smart contracts but also offers theoretical and practical guidance for further enhancing the security of blockchain applications.

关键词： Codes Smart contracts software quality Inspection Boosting Complexity theory software reliability Security Logic Business

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：