检索结果-内蒙古大学图书馆

IEEE Symposium on Security and Privacy

作者： Yechao Zhang Shengshan Hu Leo Yu Zhang Junyu Shi Minghui Li Xiaogeng Liu Wei Wan Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University School of Software Engineering Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Adversarial examples for deep neural networks (DNNs) are transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical *** this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient *** on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifests in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the

关键词： Training Privacy Buildings Closed box Minimization Data augmentation Robustness

来源：评论

学校读者我要写书评

暂无评论

MISA: Unveiling the Vulnerabilities in Split Federated Learning

MISA: Unveiling the Vulnerabilities in Split Federated Learn...

引用

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

作者： Wei Wan Yuxuan Ning Shengshan Hu Lulu Xue Minghui Li Leo Yu Zhang Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University Cluster and Grid Computing Lab

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

Securely Fine-tuning Pre-trained Encoders Against Adversaria...

引用

IEEE Symposium on Security and Privacy

作者： Ziqi Zhou Minghui Li Wei Liu Shengshan Hu Yechao Zhang Wei Wan Lulu Xue Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the *** this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six d

关键词： Training Adaptation models Sensitivity Accuracy Self-supervised learning Genetics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

arXiv

引用

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

BADROBOT: JAILBREAKING EMBODIED LLMS IN THE PHYSICAL WORLD

arXiv

引用

arXiv 2024年

作者： Zhang, Hangtao Zhu, Chenyu Wang, Xianlong Zhou, Ziqi Yin, Changgan Li, Minghui Xue, Lulu Wang, Yichen Hu, Shengshan Liu, Aishan Guo, Peijin Zhang, Leo Yu National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Beihang University China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BADROBOT, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge’s flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BADROBOT’s attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BADROBOT. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Study on Potability Water Quality Classification Based on Integrated Learning 16

Study on Potability Water Quality Classification Based on In...

引用

16th IEEE International Conference on Intelligent systems and Knowledge engineering, ISKE 2021

作者： Fen, Li Fen Lei, Zhou Ting, Chen Huaiyin Institute of Technology Faculty of Computer and Software Engineering Research Center for Logic and Intelligent Computation National-Local Joint Engineering Lab of System Credibility Automatic Verification Huaian China

ISBN: (纸本)9781665405539

Aiming at the problem of low accuracy of simple classification model, based on the drinking water data set of kaggle official website, integrated learning models is proposed, which improves the precision and accuracy of binary classification of drinking water quality. K-fold cross validation was performed to measure model consistency. The effect of set classifier is higher than that of simple classifier. © 2021 IEEE.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

arXiv

引用

arXiv 2024年

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Our code is available at https://***/Gp1g/FedAA. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fast Division Algorithm for Finite Real Number 16

Fast Division Algorithm for Finite Real Number

引用

16th IEEE International Conference on Intelligent systems and Knowledge engineering, ISKE 2021

作者： Chen, Ting Li, Fenfen Lin, Jinbao National-Local Joint Engineering Lab of System Credibility Automatic Verification Huaiyin Institute of Technology Faculty of Computer and Software Engineering Research Center for Logic and Intelligent Computation Huai'an China

ISBN: (纸本)9781665405539

The data representation and division for finite real number in computers has always been a hot topic in the fields of scientific research and engineering technology. With the research of existing real number division algorithm, design, improvement and adjustment for data structure, algorithm and programming language, and realize the fast division for finite real number. The algorithm can apply to the engineering requirement of finite real number of 506 bits. It replaces the commonly used trial division method with a comparison method, reducing the time complexity of the algorithm. The experimental results demonstrate the correctness and efficiency of the algorithm. The division of the algorithm uses comparison instead of trial division, which reduces the time complexity of the algorithm from O(n2) to O(n). The experimental results show that the algorithm is correct and efficient. © 2021 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

arXiv

引用

arXiv 2025年

作者： Bi, Zhangqian Wan, Yao Chu, Zhaoyang Hu, Yufei Zhang, Junyi Zhang, Hongyu Xu, Guandong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

How to Select Pre-Trained Code Models for Reuse? A Learning ...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Zhangqian Bi Yao Wan Zhaoyang Chu Yufei Hu Junyi Zhang Hongyu Zhang Guandong Xu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is compu-tationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks.

关键词： Phase change materials Analytical models Adaptation models Codes Costs Computational modeling Training data Machine learning software software development management

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：