检索结果-内蒙古大学图书馆

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

作者： Zeyu Xiong Daizong Liu Pan Zhou Jiahao Zhu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wangxuan Institute of Computer Technology Peking University

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets’ behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed.

关键词： Solid modeling Target tracking Three-dimensional displays Grounding Benchmark testing Signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos

You Can Ground Earlier than See: An Effective and Efficient ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiang Fang Daizong Liu Pan Zhou Guoshun Nan Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Peking University Beijing University of Posts and Telecommunications

Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual features extracted from the consecutive decoded frames and fail to handle the compressed videos for query modelling, suffering from insufficient representation capability and significant computational complexity during training and testing. In this paper, we pose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input. To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding. Particularly, instead of encoding the whole decoded frames like previous works, we capture the appearance representation by only learning the I-frame feature to reduce delay or latency. Besides, we explore the motion information not only by learning the motion vector feature, but also by exploring the relations of neighboring frames via the residual feature. In this way, a three-branch spatial-temporal attention layer with an adaptive motion-appearance fusion module is further designed to extract and aggregate both appearance and motion information for the final grounding. Experiments on three challenging datasets shows that our TCSF achieves better performance than other state-of-the-art methods with lower complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs

arXiv

引用

arXiv 2024年

作者： Zhao, Jian Wang, Shenao Zhao, Yanjie Hou, Xinyi Wang, Kailong Gao, Peiming Zhang, Yuanchao Wei, Chen Wang, Haoyu Huazhong University of Science and Technology Wuhan China MYbank Ant Group Hangzhou China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China

The proliferation of pre-trained models (PTMs) and datasets has led to the emergence of centralized model hubs like Hugging Face, which facilitate collaborative development and reuse. However, recent security reports have uncovered vulnerabilities and instances of malicious attacks within these platforms, highlighting growing security concerns. This paper presents the first systematic study of malicious code poisoning attacks on pre-trained model hubs, focusing on the Hugging Face platform. We conduct a comprehensive threat analysis, develop a taxonomy of model formats, and perform root cause analysis of vulnerable formats. While existing tools like Fickling and ModelScan offer some protection, they face limitations in semantic-level analysis and comprehensive threat detection. To address these challenges, we propose MalHug, an end-to-end pipeline tailored for Hugging Face that combines dataset loading script extraction, model deserialization, in-depth taint analysis, and heuristic pattern matching to detect and classify malicious code poisoning attacks in datasets and models. In collaboration with Ant Group, a leading financial technology company, we have implemented and deployed MalHug on a mirrored Hugging Face instance within their infrastructure, where it has been operational for over three months. During this period, MalHug has monitored more than 705K models and 176K datasets, uncovering 91 malicious models and 9 malicious dataset loading scripts. These findings reveal a range of security threats, including reverse shell, browser credential theft, and system reconnaissance. This work not only bridges a critical gap in understanding the security of the PTM supply chain but also provides a practical, industry-tested solution for enhancing the security of pre-trained model hubs. Copyright © 2024, The Authors. All rights reserved.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Driving Performance Analysis for Connected Vehicle Platoons: Velocity Perturbation and Fuel Consumption

Driving Performance Analysis for Connected Vehicle Platoons:...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Yihan Zhao Xuting Duan Jianshan Zhou Long Zhang State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing China State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Zhongguancun Laboratory School of Transportation Science and Engineering Beihang University Beijing China National Key Laboratory of Science and Technology on Information System Security Institute of Systems Engineering Beijing China

Vehicle platoon is one of the concrete manifestations of multi-vehicle cooperative control and intelligent transportation. However, the velocity perturbation in the driving process will bring about stability and safety problems. The connected autonomous vehicles (CAVs) can obtain the motion status of the lead vehicle in real time and respond to it in time, which is of far-reaching significance to platoon control. Based on this, this paper focuses on the longitudinal driving strategy of connected autonomous vehicle platoons. Specifically, we provide a discrete double-integral model controller for each vehicle in a generic scenario, and the controller performs acceleration and deceleration control at each timeslot according to the state of the vehicle in front and its own state. Simulation experiments are designed by varying the size of the platoon and the number of connected autonomous vehicles. The experimental results show that the introduction of connected autonomous vehicles can effectively suppress the platoon velocity perturbation, increase the stability of the platoon driving, and significantly reduce the fuel consumption at the same time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Spatio-Temporal State Estimation for Fine-Grained Adaptive Anomaly Diagnosis of Industrial Cyber-Physical systems

SSRN

引用

SSRN 2024年

作者： Sun, Haili Huang, Yan Han, Lansheng Fu, Cai Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Accurate detection and diagnosis of abnormal behaviors such as network attacks from multivariate time series (MTS) are crucial for ensuring the stable and effective operation of industrial cyber-physical systems (CPS). However, existing researches pay little attention to the logical dependencies among system working states, and have difficulties in explaining the evolution mechanisms of abnormal signals. To reveal the spatio-temporal association relationships and evolution mechanisms of the working states of industrial CPS, this paper proposes a fine-grained adaptive anomaly diagnosis method (i.e. MAD-Transformer) to identify and assess anomalies in MTS. A temporal and spatial state matrix are constructed to characterize state changes and inter-sensor correlations for precise anomaly localization. Subsequently, a three-branch structure of series-temporal-spatial attention module is designed to simultaneously capture the series, temporal, and spatial dependencies among MTS. Three associated alignment loss and a reconstruction loss are constructed to jointly optimize the model. Finally, anomalies are determined and diagnosed by comparing the residual matrices with the original matrices. Comparative experiments on five publicly datasets along with a petroleum refining simulation dataset demonstrate that MAD-Transformer can adaptively detect fine-grained anomalies with short duration, and outperforms the state-of-the-art baselines in terms of noise robustness and localization performance. © 2024, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Shi, Liangtao Zhong, Bineng Liang, Qihua Hu, Xiantao Mo, Zhiyi Song, Shuxiang Ministry of Education Guangxi Normal University Key Laboratory of Education Blockchain and Intelligent Technology Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Wuzhou University School of Data Science and Software Engineering Wuzhou543002 China

Utilizing the high-level semantic information of language to compensate for the limitations of vision information is a highly regarded approach in single-object tracking. However, most existing vision-language (VL) trackers employ full-parameter fine-tuning, which can easily lead to catastrophic forgetting. Therefore, they fail to fully exploit the prior knowledge of pre-trained models from upstream tasks, resulting in unsatisfactory tracking performance. To alleviate the above problem, we propose a simple yet effective Vision-Language Tracking pipeline based on Mamba Adapter, named MAVLT, which adopts the idea of parameter-efficient fine-tuning (PEFT) to realize the interaction between vision-language modalities. This novel approach offers the following advantages: (1)The knowledge of the upstream pre-trained model is efficiently inherited by freezing its parameters. This ensures that the VL tracking framework only learns the modules for vision and language interaction, with a focus on the fusion between modalities. (2)The modal interaction between language and vision encoders is flexibly bridged in each encoder layer via proposed mamba adapter, enabling efficient interaction of visual and language information at multiple levels. Extensive experiments on five popular vision-language tracking benchmarks validate the effectiveness of the proposed MAVLT. Particularly, the MAVLT achieves 73.4% AUC score on the LaSOT benchmarks with only 0.18%(0.32M) of the total parameters updates. Code and models are available at https://***/GXNU-ZhongLab/MAVLT. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

3DHacker: Spectrum-based Decision Boundary Generation for Ha...

引用

International Conference on Computer Vision (ICCV)

作者： Yunbo Tao Daizong Liu Pan Zhou Yulai Xie Wei Du Wei Hu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wangxuan Institute of Computer Technology Peking University

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the white-box setting to iteratively update the coordinate perturbations based on gradients, or utilize the output model logits to estimate noisy gradients in the black-box setting. However, these attack methods are hard to be deployed in real-world scenarios since realistic 3D applications will not share any model details to users. Therefore, we explore a more challenging yet practical 3D attack setting, i.e., attacking point clouds with black-box hard labels, in which the attacker can only have access to the prediction label of the input. To tackle this setting, we propose a novel 3D attack method, termed 3D Hard-label attacker (3DHacker), based on the developed decision boundary algorithm to generate adversarial samples solely with the knowledge of class labels. Specifically, to construct the class-aware model decision boundary, 3DHacker first randomly fuses two point clouds of different classes in the spectral domain to craft their intermediate sample with high imperceptibility, then projects it onto the decision boundary via binary search. To restrict the final perturbation size, 3DHacker further introduces an iterative optimization strategy to move the intermediate sample along the decision boundary for generating adversarial point clouds with smallest trivial perturbations. Extensive evaluations show that, even in the challenging hard-label setting, 3DHacker still competitively outperforms existing 3D attacks regarding the attack performance as well as adversary quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Spatio-Temporal State Estimation for Fine-grained Adaptive Anomaly Diagnosis of Industrial Cyber-physical systems

arXiv

引用

arXiv 2024年

Accurate detection and diagnosis of abnormal behaviors such as network attacks from multivariate time series (MTS) are crucial for ensuring the stable and effective operation of industrial cyber-physical systems (CPS). However, existing researches pay little attention to the logical dependencies among system working states, and have difficulties in explaining the evolution mechanisms of abnormal signals. To reveal the spatio-temporal association relationships and evolution mechanisms of the working states of industrial CPS, this paper proposes a fine-grained adaptive anomaly diagnosis method (i.e. MAD-Transformer) to identify and diagnose anomalies in MTS. MAD-Transformer first constructs a temporal state matrix to characterize and estimate the change patterns of the system states in the temporal dimension. Then, to better locate the anomalies, a spatial state matrix is also constructed to capture the inter-sensor state correlation relationships within the system. Subsequently, based on these two types of state matrices, a three-branch structure of series-temporal-spatial attention module is designed to simultaneously capture the series, temporal, and space dependencies among MTS. Afterwards, three associated alignment loss functions and a reconstruction loss are constructed to jointly optimize the model. Finally, anomalies are determined and diagnosed by comparing the residual matrices with the original matrices. We conducted comparative experiments on five publicly datasets spanning three application domains (service monitoring, spatial and earth exploration, and water treatment), along with a petroleum refining simulation dataset collected by ourselves. The results demonstrate that MAD-Transformer can adaptively detect fine-grained anomalies with short duration, and outperforms the state-of-the-art baselines in terms of noise robustness and localization performance. © 2024, CC BY.

关键词： Cyber Physical system

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Network Architecture Search Framework with Adaptive Multimodal Fusion for Hand Gesture Recognition

arXiv

引用

arXiv 2024年

作者： Xia, Yizhang Song, Shihao Hou, Zhanglu Xu, Junwen Zou, Juan Liu, Yuan Yang, Shengxiang Hunan Engineering Research Center of Intelligent System Optimization and Security Key Laboratory of Intelligent Computing and Information Processing Ministry of Education of China Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Province Xiangtan411105 China The Centre for Computational Intelligence School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Hand gesture recognition (HGR) based on multimodal data has attracted considerable attention owing to its great potential in applications. Various manually designed multimodal deep networks have performed well in multimodal HGR (MHGR), but most of existing algorithms require a lot of expert experience and time-consuming manual trials. To address these issues, we propose an evolutionary network architecture search framework with the adaptive multimodel fusion (AMF-ENAS). Specifically, we design an encoding space that simultaneously considers fusion positions and ratios of the multimodal data, allowing for the automatic construction of multimodal networks with different architectures through decoding. Additionally, we consider three input streams corresponding to intra-modal surface electromyography (sEMG), intra-modal accelerometer (ACC), and inter-modal sEMG-ACC. To automatically adapt to various datasets, the ENAS framework is designed to automatically search a MHGR network with appropriate fusion positions and ratios. To the best of our knowledge, this is the first time that ENAS has been utilized in MHGR to tackle issues related to the fusion position and ratio of multimodal data. Experimental results demonstrate that AMF-ENAS achieves state-of-the-art performance on the Ninapro DB2, DB3, and DB7 datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Survivable Routing Algorithm with Hybrid Protection in Elastic Optical Networks

A Survivable Routing Algorithm with Hybrid Protection in Ela...

引用

Mobile Internet, Cloud Computing and Information security (MICCIS), International Conference on

作者： Hankun Zeng Xu Zhang Chuan Feng Xiaoxue Gong School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Institute of Intelligent Communication and Network Security Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (数字)9798350389906

ISBN: (纸本)9798350389913

Spectral efficiency is a crucial factor in the survivability of multi-class traffic in elastic optical networks (EONs). In this paper, we propose a spectrum-efficient hybrid protection scheme, namely dedicated path protection (DPP) and shared backup path protection (SBPP), to address the survivability issue in EONs. Meanwhile, we design a survivable routing, modulation level, and spectrum assignment (RMLSA) algorithm to achieve hybrid protection in EONs. The simulation results demonstrate that the proposed algorithm has a lower blocking rate and Spectrum occupation ratio.

关键词： Time-frequency analysis Spectral efficiency Simulation Modulation Information security Optical fiber networks Routing

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：