检索结果-内蒙古大学图书馆

Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation

学校读者我要写书评

暂无评论

Not All Image Regions Matter: Masked Vector Quantization for...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Mengqi Huang Zhendong Mao Quan Wang Yongdong Zhang University of Science and Technology of China Hefei China Institute of Artificial intelligence Hefei Comprehensive National Science Center Hefei China MOE Key Laboratory of Trustworthy Beijing University of Posts and Telecommunications Distributed Computing and Service Beijing China

Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. However, existing codebook learning simply models all local region information of images without distinguishing their different perceptual importance, which brings redundancy in the learned codebook that not only limits the next stage's autoregressive model's ability to model important structure but also results in high training cost and slow generation speed. In this study, we borrow the idea of importance perception from classical image coding theory and propose a novel two-stage framework, which consists of Masked Quantization VAE (MQVAE) and Stackformer, to relieve the model from modeling redundancy. Specifically, MQ-VAE incorporates an adaptive mask module for masking redundant region features before quantization and an adaptive de-mask module for recovering the original grid image feature map to faithfully reconstruct the original images after quantization. Then, Stackformer learns to predict the combination of the next code and its position in the feature map. Comprehensive experiments on various image generation validate our effectiveness and efficiency. Code will be released at https://***/CrossmodalGroup/MaskedVectorQuantization.

关键词：

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Construction and Application of the SMART Model for Adaptive Industrial Data Collection Based on Knowledge Graphs

学校读者我要写书评

暂无评论

Construction and Application of the SMART Model for Adaptive...

IEEE International Conference on Big Data

作者： Wendan Cheng Zhen Zhang Heng Qian Qiuyue Wang Guanqun Su Lingge Meng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shu Ju (Shandong) Intelligent Technology Co. Ltd. Jinan China Shandong Standard Institute of Emerging Technologies and Innovations Co. Ltd. Jinan China Shandong Qingniao IIoT Co. Ltd. Jinan China

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Industrial data collection is the foundation for implementing enterprise digitization, which is of great significance to the development of intelligent manufacturing. However, Industrial Data Collection Standards (IDCS) are primarily published in paper or PDF formats, which makes it challenging to associate and reuse knowledge. This brings difficulties to data collection and management of heterogeneous devices, thus affecting the adaptive collection of industrial data. For this reason, this paper introduces SMART into industrial data collection and proposes the construction and application of a knowledge graph-based SMART Model. First, ontology semantic reasoning and natural language processing techniques are utilized to develop an ontology model for industrial data collection and extract fine-grained IDCS knowledge. Then, the knowledge is integrated according to the standard primitive structure and conceptual reasoning rules by constructing a standard association model to form the Industrial Data Collection Standards Knowledge Graph (IDCS-KG). Finally, the SMART competence level is quantitatively assessed based on the completion degree of each operation within the SMART Model. An experimental case study demonstrates that the SMART Model can collect intelligent adaptive industrial data through the reasoning and analysis of equipment adaptation protocols and data quality management strategies.

关键词： Adaptation models Analytical models Protocols Knowledge graphs Data collection Ontologies Data models Cognition Natural language processing Standards

DL-SLOT: Dynamic LiDAR SLAM and object tracking based on collaborative graph optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Xuebo Zhu, Zhongyang Zhao, Junqiao Tian, Gengxuan Ye, Chen Department of Computer Science and Technology School of Electronics and Information Engineering Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Institute of Intelligent Vehicles Tongji University Shanghai China

Ego-pose estimation and dynamic object tracking are two critical problems for autonomous driving systems. The solutions to these problems are generally based on their respective assumptions, i.e., the static world assumption for simultaneous localization and mapping (SLAM) and the accurate ego-pose assumption for object tracking. However, these assumptions are challenging to hold in dynamic road scenarios, where SLAM and object tracking become closely correlated. Therefore, we propose DL-SLOT, a dynamic LiDAR SLAM and object tracking method, to simultaneously address these two coupled problems. This method integrates the state estimations of both the autonomous vehicle and the stationary and dynamic objects in the environment into a unified optimization framework. First, we used object detection to identify all points belonging to potentially dynamic objects. Subsequently, a LiDAR odometry was conducted using the filtered point cloud. Simultaneously, we proposed a sliding window-based object association method that accurately associates objects according to the historical trajectories of tracked objects. The ego-states and those of the stationary and dynamic objects are integrated into the sliding window-based collaborative graph optimization. The stationary objects are subsequently restored from the potentially dynamic object set. Finally, a global pose-graph is implemented to eliminate the accumulated error. Experiments on KITTI datasets demonstrate that our method achieves better accuracy than SLAM and object tracking baseline methods. This confirms that solving SLAM and object tracking simultaneously is mutually advantageous, dramatically improving the robustness and accuracy of SLAM and object tracking in dynamic road scenarios. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical radar

LAMPT: LAbel Mask-Predicted Transformer for Extreme Multi-label Text Classification

学校读者我要写书评

暂无评论

LAMPT: LAbel Mask-Predicted Transformer for Extreme Multi-la...

IEEE International Conference on Big Data

作者： Yifan Xu Minghao Zhu Junli Wang Chungang Yan Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education. National (Province-Ministry Joint) Collaborative Innovation Center for Financial Network Security Tongji University Shanghai China

ISBN: (纸本)9781665480468

Extreme Multi-label text Classification ( XMC) is a task of recalling the most relevant labels for each given text from an extremely large-scale label set. It is emphasized that XMC is a more complex classification task because there are two main problems: large space of labels and the labels in XMC tasks tend to be correlated. Existing methods attempt to model label correlations by viewing the XMC task as a sequence generation problem however they still suffer from (1) using the slow serial decoding strategy where labels are predicted one-by-one. (2) needing to compare a mass of label ordering strategies in the decoding stage to achieve satisfied accuracy. In this work, we propose LAbel Mask-Predicted Transformer (LAMPT) to address the both issues, which is a novel non-autoregressive generation model that (1) enriches the input raw text representation with the additional label features by fully exploiting the label dependencies, (2) allows for efficient parallel decoding thanks to its non-autoregressive decoding formulation and mask-prediced training strategy. Experimental results demonstrate that single model performance is substantially enhanced by LAMPT. On a Wiki dataset with thirty-one thousand labels, LAMPT-XLNet accuracy has gained 1.6% relative improvement on P@3 over the LightXML-XLNet. Also, the P@1 of ensemble LAMPT is 90.00%, a significant i mprovement over the state-of-the-art ensemble LightXML (transformer-based) and AttentionXML (LSTM-based), which achieve 89.45% and 87.47%, respectively.

关键词： Training Correlation Text categorization Information services Big Data Predictive models Transformers

A permission generation and configuration method based on Rules and FP-Growth algorithm

学校读者我要写书评

暂无评论

A permission generation and configuration method based on Ru...

2021 International Conference on Networking and Network Applications, NaNA 2021

作者： Zhu, Lei Zhang, Ziheng Hei, Xinhong Wang, Yichuan Yang, Ziliang Hu, Feixiong He, Ping Xi'an University of technology School of Computer Science and Engineering Shaanxi Xi'an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Shaanxi Xi'an710048 China Shenzhen Tencent Computer System Co. Ltd Shenzhen518054 China

ISBN: (纸本)9781665441582

With the development of computer technology, lots of enterprises had begun to build a data platform, and the data and its services already paly the import role in enterprises. However, the guarantee the data security is the primary task of platform, and data access control, especially the fine-grained access control model, had become an important means to enhance the security of platform. In this paper, we propose a data access permission configuration method based on rules and FP-growth. Specifically, FP-Growth algorithm is first used to obtain the frequent items and the association relations of data, which can be transformed into the enumerable permission configuration items. Then, the correspondence and frequency of data items are calculated to acquire the frequent items, the permission configuration acting on the data table columns is obtained according to the frequency of used data items. By filtering the strong association relation, the data items that are more closely related in the association relation and the corresponding data item values are finally obtained, and they are converted into the permission configuration that acts on the rows of the data table. The proposed method has been tested and verified to meet business needs, and the performance consumption is below the threshold. Moreover, it is feasible to utilize classical data mining algorithms to generate permission configuration, which has begun to apply the Blueking Data Platform. © 2021 IEEE.

关键词： Data mining

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Xiaogeng Li, Minghui Wang, Haoyu Hu, Shengshan Ye, Dengpan Jin, Hai Wu, Libing Xiao, Chaowei 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 Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China School of Cyber Science and Engineering Wuhan University China Arizona State University United States

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo)1, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Crime

Downstream-agnostic Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Ziqi Hu, Shengshan Zhao, Ruizhi Wang, Qian Zhang, Leo Yu Hou, Junhui Jin, Hai 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 Cyber Science and Engineering Wuhan University China School of Information and Communication Technology Griffith University Australia Department of Computer Science City University of Hong Kong Hong Kong National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial use. In this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://github. com/CGCL-codes/AdvEncoder. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

PMU-Leaker: Performance Monitor Unit-based Realization of Cache Side-Channel Attacks

学校读者我要写书评

暂无评论

PMU-Leaker: Performance Monitor Unit-based Realization of Ca...

Asia and South Pacific Design Automation Conference

作者： Pengfei Qiu Qiang Gao Dongsheng Wang Yongqiang Lyu Chunlu Wang Chang Liu Rihui Sun Gang Qu Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education & Tsinghua University Beijing China Tsinghua University Beijing China Harbin Institute of Technology Harbin Heilongjiang China University of Maryland College Park Maryland USA

Performance Monitor Unit (PMU) is a special hardware module in processors that contains a set of counters to record various architectural and micro-architectural events. In this paper, we propose PMU-Leaker, a novel realization of all existing cache side-channel attacks where accurate execution time measurements are replaced by information leaked through PMU. The efficacy of PMU-Leaker is demonstrated by (1) leaking the secret data stored in Intel Software Guard Extensions (SGX) with the transient execution vulnerabilities including Spectre and ZombieLoad and (2) extracting the encryption key of a victim AES performed in SGX. We perform thorough experiments on a DELL Inspiron 15–7560 laptop that has an Intel® Core™ i5-7200U processor with the Kaby Lake architecture and the results show that, among the 176 PMU counters, 24 of them are vulnerable and can be used to launch the PMU-Leaker attack.

关键词： Program processors Portable computers Side-channel attacks Lakes Phasor measurement units Time measurement Hardware