Pub Date : 2024-04-30DOI: 10.1109/TAI.2024.3395416
Hamed Rafiei;Mohammad-R. Akbarzadeh-T.
In the realm of natural language processing, hedge-embedded structures have contributed considerably by appreciating linguistic variables and distinguishing overlapped classes. This aspect of natural languages considerably affects the building of linguistically interpretable architectures for fuzzy neural networks (FNNs). Here, we propose extending the idea of hedge-embedded linguistic fuzzy neural networks (LiFNNs) to the systems identification and control paradigm. This perspective leads us to the universal approximation property for this mathematical construct using the Stone–Weierstrass theorem and the proof of stability for the resulting nonlinear system identification process using the Lyapunov function. Furthermore, the power activation functions in the membership degrees of the proposed network enable linguistic hedge interpretation and more precise learning. Finally, the proposed LiFNN, optimized using a backpropagation learning algorithm, is evaluated on several problems in function approximation (periodic functions and quadratic Hermite function), system identification (a nonlinear system), and direct adaptive control fields. Results show that memberships are more distinguishable in the proposed LiFNN, leading to $sim$ 50% less error on the average and higher granulation and interpretability.
{"title":"Hedge-Embedded Linguistic Fuzzy Neural Networks for Systems Identification and Control","authors":"Hamed Rafiei;Mohammad-R. Akbarzadeh-T.","doi":"10.1109/TAI.2024.3395416","DOIUrl":"https://doi.org/10.1109/TAI.2024.3395416","url":null,"abstract":"In the realm of natural language processing, hedge-embedded structures have contributed considerably by appreciating linguistic variables and distinguishing overlapped classes. This aspect of natural languages considerably affects the building of linguistically interpretable architectures for fuzzy neural networks (FNNs). Here, we propose extending the idea of hedge-embedded linguistic fuzzy neural networks (LiFNNs) to the systems identification and control paradigm. This perspective leads us to the universal approximation property for this mathematical construct using the Stone–Weierstrass theorem and the proof of stability for the resulting nonlinear system identification process using the Lyapunov function. Furthermore, the power activation functions in the membership degrees of the proposed network enable linguistic hedge interpretation and more precise learning. Finally, the proposed LiFNN, optimized using a backpropagation learning algorithm, is evaluated on several problems in function approximation (periodic functions and quadratic Hermite function), system identification (a nonlinear system), and direct adaptive control fields. Results show that memberships are more distinguishable in the proposed LiFNN, leading to \u0000<inline-formula><tex-math>$sim$</tex-math></inline-formula>\u000050% less error on the average and higher granulation and interpretability.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-30DOI: 10.1109/TAI.2024.3395231
Jie Song;Zexin Zhang;Zirui Tang;Shi Feng;Yu Gu
Code summarization aims to generate natural language (NL) summaries automatically given the source code snippet, which aids developers in understanding source code faster and improves software maintenance. Recent approaches using NL techniques in code summarization fall short of adequately capturing the syntactic characteristics of programming languages (PLs), particularly the position-related syntax, from which the semantics of the source code can be extracted. In this article, we present Syntax transforMer (SyMer) based on the transformer architecture where we enhance it with position-related syntax complement (PSC) to better capture syntactic characteristics. PSC takes advantage of unambiguous relations among code tokens in abstract syntax tree (AST), as well as the gathered attention on crucial code tokens indicated by its syntactic structure. The experimental results demonstrate that SyMer outperforms state-of-the-art models by at least 2.4% bilingual evaluation understudy (BLEU), 1.0% metric for evaluation of translation with explicit ORdering (METEOR) on Java benchmark, and 4.8% (BLEU), 5.1% (METEOR), and 3.2% recall-oriented understudy for gisting evaluation - longest common subsequence (ROUGE-L) on Python benchmark.
{"title":"Improving Code Summarization With Tree Transformer Enhanced by Position-Related Syntax Complement","authors":"Jie Song;Zexin Zhang;Zirui Tang;Shi Feng;Yu Gu","doi":"10.1109/TAI.2024.3395231","DOIUrl":"https://doi.org/10.1109/TAI.2024.3395231","url":null,"abstract":"Code summarization aims to generate natural language (NL) summaries automatically given the source code snippet, which aids developers in understanding source code faster and improves software maintenance. Recent approaches using NL techniques in code summarization fall short of adequately capturing the syntactic characteristics of programming languages (PLs), particularly the position-related syntax, from which the semantics of the source code can be extracted. In this article, we present Syntax transforMer (SyMer) based on the transformer architecture where we enhance it with position-related syntax complement (PSC) to better capture syntactic characteristics. PSC takes advantage of unambiguous relations among code tokens in abstract syntax tree (AST), as well as the gathered attention on crucial code tokens indicated by its syntactic structure. The experimental results demonstrate that SyMer outperforms state-of-the-art models by at least 2.4% bilingual evaluation understudy (BLEU), 1.0% metric for evaluation of translation with explicit ORdering (METEOR) on Java benchmark, and 4.8% (BLEU), 5.1% (METEOR), and 3.2% recall-oriented understudy for gisting evaluation - longest common subsequence (ROUGE-L) on Python benchmark.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-29DOI: 10.1109/TAI.2024.3394797
Tasnim Ahmed;Naveed Ejaz;Salimur Choudhury
Road infrastructure is essential for transportation safety and efficiency. However, the current methods for assessing road conditions, crucial for effective planning and maintenance, suffer from high costs, time-intensive procedures, infrequent data collection, and limited real-time capabilities. This article presents an efficient lightweight system to analyze road quality from video feeds in real time. The backbone of the system is EdgeFusionViT, a novel vision transformer (ViT)-based architecture that uses an attention-based late fusion mechanism. The proposed architecture outperforms lightweight convolutional neural network (CNN)-based and ViT-based models. Its practicality is demonstrated by its deployment on an edge device, the Nvidia Jetson Orin Nano, enabling real-time road analysis at 12 frames per second. EdgeFusionViT outperforms existing benchmarks, achieving an impressive accuracy of 89.76% on the road surface condition dataset (RSCD). Notably, the model maintains a commendable accuracy of 76.89% even when trained with only 2% of the dataset, demonstrating its robustness and efficiency. These findings highlight the system's potential in road infrastructure management. It aids in creating safer, more efficient transport systems through timely, accurate road condition assessments. The study sets a new benchmark and opens up possibilities for advanced machine learning in infrastructure management.
道路基础设施对运输安全和效率至关重要。然而，目前评估道路状况的方法对有效规划和维护至关重要，但却存在成本高、程序耗时、数据收集不频繁、实时性有限等问题。本文介绍了一种高效的轻量级系统，可通过视频馈送实时分析道路质量。该系统的支柱是 EdgeFusionViT，它是一种基于视觉转换器（ViT）的新型架构，采用基于注意力的后期融合机制。所提出的架构优于基于卷积神经网络（CNN）的轻量级模型和基于 ViT 的模型。通过在边缘设备 Nvidia Jetson Orin Nano 上的部署，以每秒 12 帧的速度进行实时道路分析，证明了该架构的实用性。EdgeFusionViT 超越了现有基准，在路面状况数据集（RSCD）上实现了 89.76% 的惊人准确率。值得注意的是，即使只使用 2% 的数据集进行训练，该模型也能保持 76.89% 的准确率，这证明了它的鲁棒性和高效性。这些发现凸显了该系统在道路基础设施管理方面的潜力。通过及时、准确的道路状况评估，该系统有助于创建更安全、更高效的交通系统。这项研究树立了一个新的基准，为基础设施管理中的高级机器学习开辟了可能性。
{"title":"Redefining Real-Time Road Quality Analysis With Vision Transformers on Edge Devices","authors":"Tasnim Ahmed;Naveed Ejaz;Salimur Choudhury","doi":"10.1109/TAI.2024.3394797","DOIUrl":"https://doi.org/10.1109/TAI.2024.3394797","url":null,"abstract":"Road infrastructure is essential for transportation safety and efficiency. However, the current methods for assessing road conditions, crucial for effective planning and maintenance, suffer from high costs, time-intensive procedures, infrequent data collection, and limited real-time capabilities. This article presents an efficient lightweight system to analyze road quality from video feeds in real time. The backbone of the system is EdgeFusionViT, a novel vision transformer (ViT)-based architecture that uses an attention-based late fusion mechanism. The proposed architecture outperforms lightweight convolutional neural network (CNN)-based and ViT-based models. Its practicality is demonstrated by its deployment on an edge device, the Nvidia Jetson Orin Nano, enabling real-time road analysis at 12 frames per second. EdgeFusionViT outperforms existing benchmarks, achieving an impressive accuracy of 89.76% on the road surface condition dataset (RSCD). Notably, the model maintains a commendable accuracy of 76.89% even when trained with only 2% of the dataset, demonstrating its robustness and efficiency. These findings highlight the system's potential in road infrastructure management. It aids in creating safer, more efficient transport systems through timely, accurate road condition assessments. The study sets a new benchmark and opens up possibilities for advanced machine learning in infrastructure management.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-29DOI: 10.1109/TAI.2024.3394795
Jing-Xiao Liao;Bo-Jian Hou;Hang-Cheng Dong;Hao Zhang;Xiaoge Zhang;Jinwei Sun;Shiping Zhang;Feng-Lei Fan
Inspired by the complexity and diversity of biological neurons, a quadratic neuron is proposed to replace the inner product in the current neuron with a simplified quadratic function. Employing such a novel type of neurons offers a new perspective on developing deep learning. When analyzing quadratic neurons, we find that there exists a function such that a heterogeneous network can approximate it well with a polynomial number of neurons but a purely conventional or quadratic network needs an exponential number of neurons to achieve the same level of error. Encouraged by this inspiring theoretical result on heterogeneous networks, we directly integrate conventional and quadratic neurons in an autoencoder to make a new type of heterogeneous autoencoders. To our best knowledge, it is the first heterogeneous autoencoder that is made of different types of neurons. Next, we apply the proposed heterogeneous autoencoder to unsupervised anomaly detection (AD) for tabular data and bearing fault signals. The AD faces difficulties such as data unknownness, anomaly feature heterogeneity, and feature unnoticeability, which is suitable for the proposed heterogeneous autoencoder. Its high feature representation ability can characterize a variety of anomaly data (heterogeneity), discriminate the anomaly from the normal (unnoticeability), and accurately learn the distribution of normal samples (unknownness). Experiments show that heterogeneous autoencoders perform competitively compared with other state-of-the-art models.
{"title":"Quadratic Neuron-Empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection","authors":"Jing-Xiao Liao;Bo-Jian Hou;Hang-Cheng Dong;Hao Zhang;Xiaoge Zhang;Jinwei Sun;Shiping Zhang;Feng-Lei Fan","doi":"10.1109/TAI.2024.3394795","DOIUrl":"https://doi.org/10.1109/TAI.2024.3394795","url":null,"abstract":"Inspired by the complexity and diversity of biological neurons, a quadratic neuron is proposed to replace the inner product in the current neuron with a simplified quadratic function. Employing such a novel type of neurons offers a new perspective on developing deep learning. When analyzing quadratic neurons, we find that there exists a function such that a heterogeneous network can approximate it well with a polynomial number of neurons but a purely conventional or quadratic network needs an exponential number of neurons to achieve the same level of error. Encouraged by this inspiring theoretical result on heterogeneous networks, we directly integrate conventional and quadratic neurons in an autoencoder to make a new type of heterogeneous autoencoders. To our best knowledge, it is the first heterogeneous autoencoder that is made of different types of neurons. Next, we apply the proposed heterogeneous autoencoder to unsupervised anomaly detection (AD) for tabular data and bearing fault signals. The AD faces difficulties such as data unknownness, anomaly feature heterogeneity, and feature unnoticeability, which is suitable for the proposed heterogeneous autoencoder. Its high feature representation ability can characterize a variety of anomaly data (heterogeneity), discriminate the anomaly from the normal (unnoticeability), and accurately learn the distribution of normal samples (unknownness). Experiments show that heterogeneous autoencoders perform competitively compared with other state-of-the-art models.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-18DOI: 10.1109/TAI.2024.3391230
Yan Wang;Xiaoyan Sun;Yong Zhang;Dunwei Gong;Hejuan Hu;Mingcheng Zuo
It is very challenging to autonomously generate algorithms suitable for constrained multiobjective optimization problems due to the diverse performance of existing algorithms. In this article, we propose a linear regression (LR)-based autonomous intelligent optimization method. It first extracts typical features of a constrained multiobjective optimization problem by focused sampling to form a feature vector. Then, a LR model is designed to learn the relationship between optimization problems and intelligent optimization algorithms (IOAs). Finally, the trained model autonomously generates a suitable IOA by inputting the feature vector. The proposed method is applied to six constrained multiobjective benchmark test sets with various characteristics and compared with seven popular optimization algorithms. The experimental results verify the effectiveness of the proposed method. In addition, the proposed method is used to solve the operation optimization problems of an integrated coal mine energy system, and the experimental results show its practicability.
由于现有算法的性能参差不齐，要自主生成适用于受限多目标优化问题的算法非常具有挑战性。本文提出了一种基于线性回归（LR）的自主智能优化方法。它首先通过集中采样提取约束多目标优化问题的典型特征，形成特征向量。然后，设计一个 LR 模型来学习优化问题与智能优化算法（IOA）之间的关系。最后，训练有素的模型通过输入特征向量自主生成合适的 IOA。所提出的方法被应用于六个具有不同特征的受限多目标基准测试集，并与七种流行的优化算法进行了比较。实验结果验证了所提方法的有效性。此外，还将所提方法用于解决煤矿综合能源系统的运行优化问题，实验结果表明了该方法的实用性。
{"title":"Linear Regression-Based Autonomous Intelligent Optimization for Constrained Multiobjective Problems","authors":"Yan Wang;Xiaoyan Sun;Yong Zhang;Dunwei Gong;Hejuan Hu;Mingcheng Zuo","doi":"10.1109/TAI.2024.3391230","DOIUrl":"https://doi.org/10.1109/TAI.2024.3391230","url":null,"abstract":"It is very challenging to autonomously generate algorithms suitable for constrained multiobjective optimization problems due to the diverse performance of existing algorithms. In this article, we propose a linear regression (LR)-based autonomous intelligent optimization method. It first extracts typical features of a constrained multiobjective optimization problem by focused sampling to form a feature vector. Then, a LR model is designed to learn the relationship between optimization problems and intelligent optimization algorithms (IOAs). Finally, the trained model autonomously generates a suitable IOA by inputting the feature vector. The proposed method is applied to six constrained multiobjective benchmark test sets with various characteristics and compared with seven popular optimization algorithms. The experimental results verify the effectiveness of the proposed method. In addition, the proposed method is used to solve the operation optimization problems of an integrated coal mine energy system, and the experimental results show its practicability.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-16DOI: 10.1109/TAI.2024.3356669
K. P. Suba Subbalakshmi;Wojciech Samek;Xia Ben Hu
This special issue brings together seven articles that address different aspects of explainable and interpretable artificial intelligence (AI). Over the years, machine learning (ML) and AI models have posted strong performance across several tasks. This has sparked interest in deploying these methods in critical applications like health and finance. However, to be deployable in the field, ML and AI models must be trustworthy. Explainable and interpretable AI are two areas of research that have become increasingly important to ensure trustworthiness and hence deployability of advanced AI and ML methods. Interpretable AI are models that obey some domain-specific constraints so that they are better understandable by humans. In essence, they are not black-box models. On the other hand, explainable AI refers to models and methods that are typically used to explain another black-box model.
本特刊汇集了七篇文章，探讨了可解释和可解释人工智能（AI）的不同方面。多年来，机器学习（ML）和人工智能模型在多项任务中表现出色。这激发了人们将这些方法部署到健康和金融等关键应用领域的兴趣。然而，要在该领域部署，ML 和 AI 模型必须值得信赖。可解释人工智能和可解释人工智能是两个日益重要的研究领域，可确保先进人工智能和 ML 方法的可信度和可部署性。可解释的人工智能模型遵从某些特定领域的约束条件，因此更容易被人类理解。从本质上讲，它们不是黑盒模型。另一方面，可解释人工智能指的是通常用于解释另一个黑盒模型的模型和方法。
{"title":"Guest Editorial: New Developments in Explainable and Interpretable Artificial Intelligence","authors":"K. P. Suba Subbalakshmi;Wojciech Samek;Xia Ben Hu","doi":"10.1109/TAI.2024.3356669","DOIUrl":"https://doi.org/10.1109/TAI.2024.3356669","url":null,"abstract":"This special issue brings together seven articles that address different aspects of explainable and interpretable artificial intelligence (AI). Over the years, machine learning (ML) and AI models have posted strong performance across several tasks. This has sparked interest in deploying these methods in critical applications like health and finance. However, to be deployable in the field, ML and AI models must be trustworthy. Explainable and interpretable AI are two areas of research that have become increasingly important to ensure trustworthiness and hence deployability of advanced AI and ML methods. Interpretable AI are models that obey some domain-specific constraints so that they are better understandable by humans. In essence, they are not black-box models. On the other hand, explainable AI refers to models and methods that are typically used to explain another black-box model.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10500898","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140559370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-16DOI: 10.1109/TAI.2024.3389611
Hezhe Sun;Yufei Wang;Huiwen Yang;Kaixuan Huo;Yuzhe Li
Privacy-aware machine learning paradigms have sparked widespread concern due to their ability to safeguard the local privacy of data owners, preventing the leakage of private information to untrustworthy platforms or malicious third parties. This article focuses on characterizing the interactions between the learner and the data owner within this privacy-aware training process. Here, the data owner hesitates to transmit the original gradient to the learner due to potential cybersecurity issues, such as gradient leakage and membership inference. To address this concern, we propose a Stackelberg game framework that models the training process. In this framework, the data owner's objective is not to maximize the discrepancy between the learner's obtained gradient and the true gradient but rather to ensure that the learner obtains a gradient closely resembling one deliberately designed by the data owner, while the learner's objective is to recover the true gradient as accurately as possible. We derive the optimal encoder and decoder using mismatched cost functions and characterize the equilibrium for specific cases, balancing model accuracy and local privacy. Numerical examples illustrate the main results, and we conclude with expanding discussions to suggest future investigations into reliable countermeasure designs.
{"title":"Strategic Gradient Transmission With Targeted Privacy-Awareness in Model Training: A Stackelberg Game Analysis","authors":"Hezhe Sun;Yufei Wang;Huiwen Yang;Kaixuan Huo;Yuzhe Li","doi":"10.1109/TAI.2024.3389611","DOIUrl":"https://doi.org/10.1109/TAI.2024.3389611","url":null,"abstract":"Privacy-aware machine learning paradigms have sparked widespread concern due to their ability to safeguard the local privacy of data owners, preventing the leakage of private information to untrustworthy platforms or malicious third parties. This article focuses on characterizing the interactions between the learner and the data owner within this privacy-aware training process. Here, the data owner hesitates to transmit the original gradient to the learner due to potential cybersecurity issues, such as gradient leakage and membership inference. To address this concern, we propose a Stackelberg game framework that models the training process. In this framework, the data owner's objective is not to maximize the discrepancy between the learner's obtained gradient and the true gradient but rather to ensure that the learner obtains a gradient closely resembling one deliberately designed by the data owner, while the learner's objective is to recover the true gradient as accurately as possible. We derive the optimal encoder and decoder using mismatched cost functions and characterize the equilibrium for specific cases, balancing model accuracy and local privacy. Numerical examples illustrate the main results, and we conclude with expanding discussions to suggest future investigations into reliable countermeasure designs.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-16DOI: 10.1109/TAI.2024.3388389
Mingfu Xue;Xin Wang;Yinghao Wu;Shifeng Ni;Leo Yu Zhang;Yushu Zhang;Weiqiang Liu
Intellectual property (IP) protection for deep neural networks (DNNs) has raised serious concerns in recent years. Most existing works embed watermarks in the DNN model for IP protection, which need to modify the model and do not consider/mention interpretability. In this article, for the first time, we propose an interpretable IP protection method for DNN based on explainable artificial intelligence. Compared with existing works, the proposed method does not modify the DNN model, and the decision of the ownership verification is interpretable. We extract the intrinsic features of the DNN model by using deep Taylor decomposition. Since the intrinsic feature is composed of unique interpretation of the model's decision, the intrinsic feature can be regarded as fingerprint of the model. If the fingerprint of a suspected model is the same as the original model, the suspected model is considered as a pirated model. Experimental results demonstrate that the fingerprints can be successfully used to verify the ownership of the model and the test accuracy of the model is not affected. Furthermore, the proposed method is robust to fine-tuning attack, pruning attack, watermark overwriting attack, and adaptive attack.
{"title":"An Explainable Intellectual Property Protection Method for Deep Neural Networks Based on Intrinsic Features","authors":"Mingfu Xue;Xin Wang;Yinghao Wu;Shifeng Ni;Leo Yu Zhang;Yushu Zhang;Weiqiang Liu","doi":"10.1109/TAI.2024.3388389","DOIUrl":"https://doi.org/10.1109/TAI.2024.3388389","url":null,"abstract":"Intellectual property (IP) protection for deep neural networks (DNNs) has raised serious concerns in recent years. Most existing works embed watermarks in the DNN model for IP protection, which need to modify the model and do not consider/mention interpretability. In this article, for the first time, we propose an interpretable IP protection method for DNN based on explainable artificial intelligence. Compared with existing works, the proposed method does not modify the DNN model, and the decision of the ownership verification is interpretable. We extract the intrinsic features of the DNN model by using deep Taylor decomposition. Since the intrinsic feature is composed of unique interpretation of the model's decision, the intrinsic feature can be regarded as fingerprint of the model. If the fingerprint of a suspected model is the same as the original model, the suspected model is considered as a pirated model. Experimental results demonstrate that the fingerprints can be successfully used to verify the ownership of the model and the test accuracy of the model is not affected. Furthermore, the proposed method is robust to fine-tuning attack, pruning attack, watermark overwriting attack, and adaptive attack.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Advances in deep generative models shed light on de novo molecule generation with desired properties. However, molecule generation targeted for dual protein targets still faces formidable challenges including insufficient protein 3-D structure data requisition for conditioned model training, inflexibility of auto-regressive sampling, and model generalization to unseen targets. Here, this study proposed diffusion model for dual targets-based molecule generation (DiffDTM), a novel unified structure-free deep generative framework based on a diffusion model for dual-target based molecule generation to address the above issues. Specifically, DiffDTM receives representations of protein sequences and molecular graphs pretrained on large-scale datasets as inputs instead of protein and molecular conformations and incorporates an information fusion module to achieve conditional generation in a one-shot manner. We perform comprehensive multiview experiments to demonstrate that DiffDTM can generate druglike, synthesis-accessible, novel, and high-binding affinity molecules targeting specific dual proteins, outperforming the state-of-the-art (SOTA) models in terms of multiple evaluation metrics. Furthermore, DiffDTM could directly generate molecules toward dopamine receptor D2 (DRD2) and 5-hydroxytryptamine receptor 1A (HTR1A) as new antipsychotics. Experimental comparisons highlight the generalizability of DiffDTM to easily adapt to unseen dual targets and generate bioactive molecules, addressing the issues of insufficient active molecule data for model training when new targets are encountered.
{"title":"A Unified Conditional Diffusion Framework for Dual Protein Targets-Based Bioactive Molecule Generation","authors":"Lei Huang;Zheng Yuan;Huihui Yan;Rong Sheng;Linjing Liu;Fuzhou Wang;Weidun Xie;Nanjun Chen;Fei Huang;Songfang Huang;Ka-Chun Wong;Yaoyun Zhang","doi":"10.1109/TAI.2024.3387402","DOIUrl":"https://doi.org/10.1109/TAI.2024.3387402","url":null,"abstract":"Advances in deep generative models shed light on \u0000<italic>de novo</i>\u0000 molecule generation with desired properties. However, molecule generation targeted for dual protein targets still faces formidable challenges including insufficient protein 3-D structure data requisition for conditioned model training, inflexibility of auto-regressive sampling, and model generalization to unseen targets. Here, this study proposed diffusion model for dual targets-based molecule generation (DiffDTM), a novel unified structure-free deep generative framework based on a diffusion model for dual-target based molecule generation to address the above issues. Specifically, DiffDTM receives representations of protein sequences and molecular graphs pretrained on large-scale datasets as inputs instead of protein and molecular conformations and incorporates an information fusion module to achieve conditional generation in a one-shot manner. We perform comprehensive multiview experiments to demonstrate that DiffDTM can generate druglike, synthesis-accessible, novel, and high-binding affinity molecules targeting specific dual proteins, outperforming the state-of-the-art (SOTA) models in terms of multiple evaluation metrics. Furthermore, DiffDTM could directly generate molecules toward dopamine receptor D2 (DRD2) and 5-hydroxytryptamine receptor 1A (HTR1A) as new antipsychotics. Experimental comparisons highlight the generalizability of DiffDTM to easily adapt to unseen dual targets and generate bioactive molecules, addressing the issues of insufficient active molecule data for model training when new targets are encountered.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-10DOI: 10.1109/TAI.2024.3386498
Varun Kohli;Muhammad Naveed Aman;Biplab Sikdar
The Internet of Things (IoT) has been a popular topic for research and development in the past decade. The resource-constrained and wireless nature of IoT devices presents a large surface of vulnerabilities, and traditional network security methods involving complex cryptography are not feasible. Studies show that Denial of Service (DoS), physical intrusion, spoofing, and node forgery are prevalent threats in the IoT, and there is a need for robust, lightweight device fingerprinting schemes. We identify eight criteria of effective fingerprinting methods for resource-constrained IoT devices and propose an intelligent, lightweight, whitelist-based fingerprinting method that satisfies these properties. The proposed method uses the power-up Static Random Access Memory (SRAM) stack as fingerprint features and autoencoder networks (AEN) for fingerprint registration and verification. We also present a threat mitigation framework based on network isolation levels to handle potential and identified threats. Experiments are conducted with a heterogeneous pool of 10 advanced virtual reduced instruction set computer (AVR) Harvard architecture prover devices from different vendors, and Dell Latitude and Dell XPS 13 laptops are used as verifier testbeds. The proposed method has a 99.9% accuracy, 100% precision, and 99.6% recall on known and unknown heterogeneous devices, which is an improvement over several past works. The independence of fingerprints stored in the AENs enables easy distribution and update, and the observed evaluation latency ( $sim$$10^{-4}$ s) and data collection latency ( $sim$$1$ s) make our method practical for real-world scenarios. Lastly, we analyze the proposed method with regard to the eight criteria and highlight its limitations for future improvement.
{"title":"An Intelligent Fingerprinting Technique for Low-Power Embedded IoT Devices","authors":"Varun Kohli;Muhammad Naveed Aman;Biplab Sikdar","doi":"10.1109/TAI.2024.3386498","DOIUrl":"https://doi.org/10.1109/TAI.2024.3386498","url":null,"abstract":"The Internet of Things (IoT) has been a popular topic for research and development in the past decade. The resource-constrained and wireless nature of IoT devices presents a large surface of vulnerabilities, and traditional network security methods involving complex cryptography are not feasible. Studies show that Denial of Service (DoS), physical intrusion, spoofing, and node forgery are prevalent threats in the IoT, and there is a need for robust, lightweight device fingerprinting schemes. We identify eight criteria of effective fingerprinting methods for resource-constrained IoT devices and propose an intelligent, lightweight, whitelist-based fingerprinting method that satisfies these properties. The proposed method uses the power-up Static Random Access Memory (SRAM) stack as fingerprint features and autoencoder networks (AEN) for fingerprint registration and verification. We also present a threat mitigation framework based on network isolation levels to handle potential and identified threats. Experiments are conducted with a heterogeneous pool of 10 advanced virtual reduced instruction set computer (AVR) Harvard architecture prover devices from different vendors, and Dell Latitude and Dell XPS 13 laptops are used as verifier testbeds. The proposed method has a 99.9% accuracy, 100% precision, and 99.6% recall on known and unknown heterogeneous devices, which is an improvement over several past works. The independence of fingerprints stored in the AENs enables easy distribution and update, and the observed evaluation latency (\u0000<inline-formula><tex-math>$sim$</tex-math></inline-formula>\u0000 \u0000<inline-formula><tex-math>$10^{-4}$</tex-math></inline-formula>\u0000 s) and data collection latency (\u0000<inline-formula><tex-math>$sim$</tex-math></inline-formula>\u0000 \u0000<inline-formula><tex-math>$1$</tex-math></inline-formula>\u0000 s) make our method practical for real-world scenarios. Lastly, we analyze the proposed method with regard to the eight criteria and highlight its limitations for future improvement.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142164998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：