检索结果-内蒙古大学图书馆

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Li, Bowen Song, Yufei Yu, Zhifei Hu, Shengshan Wan, Wei Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs' attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Text-guided Reconstruction Network for Sentiment Analysis with Uncertain Missing Modalities

学校读者我要写书评

暂无评论

IEEE Transactions on Affective computing 2025年

作者： Shi, Piao Hu, Min Nakagawa, Satoshi Zheng, Xiangming Shi, Xuefeng Ren, Fuji Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine National Smart Eldercare International Science and Technology Cooperation Base School of Computer Science and Information Engineering Anhui Hefei230601 China Bozhou University School of Electronic and Information Engineering Bozhou236800 China University of Tokyo Graduate School of Information Science and Technology Tokyo113-8656 Japan University of Electronic Science and Technology of China College of Computer Science and Engineering Chengdu611731 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518110 China

Multimodal Sentiment Analysis (MSA) is an attractive research that aims to integrate sentiment expressed in textual, visual, and acoustic signals. There are two main problems in the existing methods: 1) the dominant role of the text is underutilization in unaligned multimodal data, and 2) the modality under uncertain missing feature is not sufficiently explored. This paper proposes a Text-guided Reconstruction Network (TgRN) for MSA with uncertain missing modalities in non-aligned sequences. The TgRN network includes three primary modules: Text-guided Extraction Module (TEM), Reconstruction Module (RM) and Text-guided Fusion Module (TFM). First, the TEM consists of the text-guided cross attention units and self-attention units to capture inter-modal features and intra-modal features, respectively. Second, leveraging enhanced attention units and a three-way squeeze-and-excitation block, the RM is designed to learn semantic information from incomplete data and reconstruct missing modality features. Third, the TFM utilizes a progressive modality-mixing adaptation gate to explore the dynamic correlations between nonverbal and verbal modalities, effectively addressing the modality gap issue. Finally, under the supervision of sentiment prediction loss and reconstruction loss, the TgRN effectively processes both uncertain missing-modality conditions and ideal complete modality conditions. Extensive experiments on CMU-MOSI and CH-SIMS demonstrate that our proposed method outperforms state-of-the-art approaches. © 2010-2012 IEEE.

关键词： Semantics

Wiki-match:A multi-model pipeline for image-caption matching task on Wikipedia dataset

学校读者我要写书评

暂无评论

Wiki-match:A multi-model pipeline for image-caption matching...

作者： Yibing Chen Siyu Lei Zhouhang Sun School of Computing and Information System Singapore Management University School of Computer Science Sichuan University School of Data Science The Chinese University of Hongkong(Shenzhen)

We propose a multi-model pipeline for image-caption matching tasks on Wikipediabased dataset which leverages object-detection technique and attention mechanism to achieve fine-grained matching between textual representation and image *** from the prior research,we not only evaluate our pipeline effectiveness on common benchmark dataset such as MS-COCO and Flickr30k,but also a new dataset that is derived from Wikipedia which is rich in natural entities and abstract *** findings show:1) our model pipeline improves R@1 by 113.4%,R@3 by 86.1%,and R@5 by 114.4% compared to the original pipeline provided by the Wikipedia-based dataset.2) our model pipeline has close to the state-of-the-art performance in common benchmark dataset including Flickr30k and MS-COCO.3) images that are from Wikipedia creates bigger challenges for models to understand compares to MS-COCO or Flickr30k due to the abstract concepts and broad topics covered by Wikipedia.

关键词：

A Wavelet-Guided Deep Unfolding Network for Single Image Reflection Removal

学校读者我要写书评

暂无评论

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 34卷 4040-4051页

作者： Ya-Nan Zhang Qiufu Li Xu Wu Nan Mu Xiaoning Li Linlin Shen College of Computer Science and the Visual Computing and Virtual Reality Key Laboratory of Sichuan Sichuan Normal University Chengdu China Education Big Data Collaborative Innovation Center of Sichuan 2011 Chengdu Sichuan China School of Artificial Intelligence Guangdong Key Laboratory of Intelligent Information Processing and the National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Removing unwanted reflections from images is a fundamental yet challenging problem in low-level computer vision. Recent deep learning-based Single Image Reflection Removal (SIRR) methods have made significant progress. However, separating reflections from transmission content remains difficult, particularly in complex scenes where the two exhibit high visual similarity. Upon careful analysis, we find that reflections predominantly reside in the high-frequency components of an image. These reflections tend to distort fine details in the high-frequency range, while the low-frequency information remains relatively less affected. This observation motivates us to explore a frequency-aware approach for SIRR by leveraging the Discrete Wavelet Transform (DWT). The wavelet decomposition enables us to distinguish and isolate reflective artifacts in the frequency domain while preserving the transmission information. Building on this insight, we propose a novel Wavelet-guided Deep Unfolding Network (WDUNet) that leverages the strengths of wavelet decomposition and deep unfolding techniques to improve interpretability and generalization in SIRR. Specifically, we formulate an optimization-based reflection removal model using DWT and convolutional dictionaries. The proposed model is optimized via a proximal gradient algorithm and then unfolded into a neural network architecture, where all parameters are learned end-to-end during training. By combining wavelet domain analysis with deep unfolding, WDUNet enhances both the interpretability and generalization of SIRR methods. Additionally, we design and integrate the Low-frequency Parameter Estimation Module (LPEM) and High-frequency Parameter Estimation Module (HPEM) modules into WDUNet, allowing the network to automatically learn and optimize the models' hyperparameters. Extensive experiments conducted on four benchmark datasets demonstrate that WDUNet consistently outperforms existing state-of-the-art methods in both objective eval

关键词： Reflection Discrete wavelet transforms Solid modeling Feature extraction Deep learning Visualization Training Frequency-domain analysis Bars Mathematical models

Secure Cross-Domain Authentication and data Sharing Scheme for IIoT in Cloud-Fog Automation Architecture

学校读者我要写书评

暂无评论

IEEE Journal on Selected Areas in Communications 2025年

作者： Chen, Xi Hu, Chunqiang Cai, Bin Hu, Pengfei Yu, Jiguo Ministry of Education of China Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing China Chongqing University School of Big Data and Software Engineering Chongqing China Shandong University School of Computer Science and Technology Shandong China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China Qilu University of Technology Big Data Institute Jinan China

Cloud-fog automation architecture has propelled the advancement of the Industrial Internet of Things (IIoT), significantly enhancing production efficiency and intelligence through extensive data collection and connectivity. Simultaneously, industrial cyber-physical system leverages this data to achieve intelligent control and optimization of production processes. As industrial production becomes increasingly specialized and complex, independent operations within a single domain are no longer sufficient to meet demands, making cross-domain collaborative production inevitable. Consequently, ensuring the security of cross-domain communication and data sharing has become a critical issue for IIoT under the cloud-fog automation architecture. Existing solutions encounter substantial management and computational burdens in cross-domain communication and data sharing, and they are vulnerable to privacy leakage risks. To address these challenges and enhance industrial production efficiency, this paper uses consortium blockchain to co-design a cross-domain authentication and data sharing scheme. The scheme ensures secure and private cross-domain communications with minimal computational, communication, and storage overhead. And, the proposed time-specific plaintext checkable encryption protocol can secure data during cross-domain sharing. Security and performance analyses show that the proposed scheme effectively reduces computational and communication resource demands while maintaining communication and data security. © 1983-2012 IEEE.

关键词： Sensitive data

MORAL: A Multimodal Reinforcement Learning Framework for Decision Making in Autonomous Laboratories

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tirabassi, Natalie Kumar, Sathish A.P. Jha, Sumit Ramanathan, Arvind Department of Computer Science Cleveland State University ClevelandOH United States School of Computing and Information Sciences Florida International University MiamiFL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States

We propose MORAL (a multimodal reinforcement learning framework for decision making in autonomous laboratories) that enhances sequential decision-making in autonomous robotic laboratories through the integration of visual and textual inputs. Using the Bridgedata V2 dataset, we generate fine-tuned image captions with a pretrained BLIP-2 vision-language model and combine them with visual features through an early fusion strategy. The fused representations are processed using Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) agents. Experimental results demonstrate that multimodal agents achieve a 20% improvement in task completion rates and significantly outperform visual-only and textual-only baselines after sufficient training. Compared to transformer-based and recurrent multimodal RL models, our approach achieves superior performance in cumulative reward and caption quality metrics (BLEU, METEOR, ROUGE-L). These results highlight the impact of semantically aligned language cues in enhancing agent learning efficiency and generalization. The proposed framework contributes to the advancement of multimodal reinforcement learning and embodied AI systems in dynamic, real-world environments. © 2025, CC BY.

关键词： Reinforcement learning

Enhanced Penalty-based Bidirectional Reinforcement Learning Algorithms

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pula, Gana Sandeep Kumar, Sathish A.P. Jha, Sumit Ramanathan, Arvind Department of Computer Science Cleveland State University ClevelandOH United States School of Computing and Information Sciences Florida International University MiamiFL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States

This research focuses on enhancing reinforcement learning (RL) algorithms by integrating penalty functions to guide agents in avoiding unwanted actions while optimizing rewards. The goal is to improve the learning process by ensuring that agents learn not only suitable actions but also which actions to avoid. Additionally, we reintroduce a bidirectional learning approach that enables agents to learn from both initial and terminal states, thereby improving speed and robustness in complex environments. Our proposed Penalty-Based Bidirectional methodology is tested against Mani skill benchmark environments, demonstrating an optimality improvement of success rate of approximately 4% compared to existing RL implementations. The findings indicate that this integrated strategy enhances policy learning, adaptability, and overall performance in challenging scenarios. © 2025, CC BY.

关键词： Learning algorithms

ACE-RLHF: Automated Code Evaluation and Socratic Feedback Generation Tool using Large Language Models and Reinforcement Learning with Human Feedback

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Rahman, Tasnia Kumar, Sathish A.P. Jha, Sumit Ramanathan, Arvind Department of Computer Science Cleveland State University ClevelandOH United States School of Computing and Information Sciences Florida International University MiamiFL United States Data Science and Learning Division Argonne National Laboratory LemontIL United States

Automated Program Repair tools are developed for generating feedback and suggesting a repair method for erroneous code. State of the art (SOTA) code repair methods rely on data-driven approaches and often fail to deliver solution for complicated programming questions. To interpret the natural language of unprecedented programming problems, using Large Language Models (LLMs) for code-feedback generation is crucial. LLMs generate more comprehensible feedback than compiler-generated error messages, and Reinforcement Learning with Human Feedback (RLHF) further enhances quality by integrating human-in-the-loop which helps novice students to lean programming from scratch interactively. We are applying RLHF fine-tuning technique for an expected Socratic response such as a question with hint to solve the programming issue. We are proposing code feedback generation tool by fine-tuning LLM with RLHF, Automated Code Evaluation with RLHF (ACE-RLHF), combining two open-source LLM models with two different SOTA optimization techniques. The quality of feedback is evaluated on two benchmark datasets containing basic and competition-level programming questions where the later is proposed by us. We achieved 2-5% higher accuracy than RL-free SOTA techniques using Llama-3-7B-Proximal-policy optimization in automated evaluation and similar or slightly higher accuracy compared to reward model-free RL with AI Feedback (RLAIF). We achieved almost 40% higher accuracy with GPT-3.5 Best-of-n optimization while performing manual evaluation. © 2025, CC BY.

关键词： Reinforcement learning

Root-Of-Trust for Continuous Integration and Continuous Deployment Pipeline in Cloud computing

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第11期73卷 2223-2239页

作者： Abdul Saboor Mohd Fadzil Hassan Rehan Akbar Erwin Susanto Syed Nasir Mehmood Shah Muhammad Aadil Siddiqui Saeed Ahmed Magsi High-Performance Cloud Computing Centre(HPC3) Department of Computer&Information SciencesUniversiti Teknologi PETRONASSeri IskandarPerakMalaysia Centre for Research in Data Science(CeRDaS) Department of Computer&Information SciencesUniversiti Teknologi PETRONASSeri IskandarPerakMalaysia School of Electrical Engineering Telkom UniversityBandungIndonesia KICSIT Institute of Space Technology(IST)IslamabadPakistan Department of Electrical and Electronics Engineering Universiti Teknologi PETRONASSeri IskandarPerakMalaysia

Cloud computing has gained significant use over the last decade due to its several benefits,including cost savings associated with setup,deployments,delivery,physical resource sharing across virtual machines,and availability of on-demand cloud ***,in addition to usual threats in almost every computing environment,cloud computing has also introduced a set of new threats as consumers share physical resources due to the physical co-location ***,since there are a growing number of attacks directed at cloud environments(including dictionary attacks,replay code attacks,denial of service attacks,rootkit attacks,code injection attacks,etc.),customers require additional assurances before adopting cloud ***,the continuous integration and continuous deployment of the code fragments have made cloud services more prone to security *** this study,the model based on the root of trust for continuous integration and continuous deployment is proposed,instead of only relying on a single signon authentication method that typically uses only id and *** underlying study opted hardware security module by utilizing the Trusted Platform Module(TPM),which is commonly available as a cryptoprocessor on the motherboards of the personal computers and data center *** preliminary proof of concept demonstrated that the TPM features can be utilized through RESTful services to establish the root of trust for continuous integration and continuous deployment pipeline and can additionally be integrated as a secure microservice feature in the cloud computing environment.

关键词： Root of Trust(RoT) Trusted Platform Module(TPM) cryptoprocessor microservices Hardware Security Modules(HSM) DevOps