Person re-identification (Re-ID) is a classical computer vision task and has significant applications for public security and information forensics. Recently, long-term Re-ID with clothes-changing has attracted increasing attention. However, existing methods mainly focus on image-based setting, where richer temporal information is overlooked. In this paper, we focus on the relatively new yet practical problem of Clothes-Changing Video-based Re-ID (CCVReID), which is less studied. First, given the dataset shortage, we build two new benchmark datasets for CCVReID problem, including a large-scale synthetic video dataset and a real-world one, both containing human sequences with various clothing changes. Moreover, we systematically study this problem by simultaneously considering the classical appearance feature and temporal feature contained in the video. We develop a dual-branch fusion framework that makes use of the information from both clothes-aware appearance feature and clothes-free gait feature. For better information fusion, a confidence-guided re-ranking strategy is proposed to adaptively balance the weight of these two categories of features. We have released the benchmark and code proposed in this work to the public at https://github.com/kkw98/CCVReID.
{"title":"A New Benchmark and Algorithm for Clothes-Changing Video Person Re-Identification","authors":"Likai Wang;Xiangqun Zhang;Ruize Han;Yanjie Wei;Song Wang;Wei Feng","doi":"10.1109/TIFS.2025.3539079","DOIUrl":"10.1109/TIFS.2025.3539079","url":null,"abstract":"Person re-identification (Re-ID) is a classical computer vision task and has significant applications for public security and information forensics. Recently, long-term Re-ID with clothes-changing has attracted increasing attention. However, existing methods mainly focus on image-based setting, where richer temporal information is overlooked. In this paper, we focus on the relatively new yet practical problem of Clothes-Changing Video-based Re-ID (CCVReID), which is less studied. First, given the dataset shortage, we build two new benchmark datasets for CCVReID problem, including a large-scale synthetic video dataset and a real-world one, both containing human sequences with various clothing changes. Moreover, we systematically study this problem by simultaneously considering the classical appearance feature and temporal feature contained in the video. We develop a dual-branch fusion framework that makes use of the information from both clothes-aware appearance feature and clothes-free gait feature. For better information fusion, a confidence-guided re-ranking strategy is proposed to adaptively balance the weight of these two categories of features. We have released the benchmark and code proposed in this work to the public at <uri>https://github.com/kkw98/CCVReID</uri>.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"1993-2005"},"PeriodicalIF":6.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143192138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intrusion detection systems are a crucial technique for securing the Internet of Things (IoT) from malicious attacks. Additionally, due to the continuous emergence of new vulnerabilities and unknown attack types, only a small number of attack samples in the IoT environments can be captured for analysis. In this work, we introduce an anchor graph clustering (AGC) method for intrusion detection to address the challenge of limited labeled samples in the IoT environments. AGC initially transforms the raw data into the embedding space to obtain more representative anchors. Then, AGC unifies anchor graph construction, anchor graph learning, and graph clustering into a unified framework, solving the resulting optimization problem through an iterative solution algorithm. Finally, AGC leverages the powerful analytical capabilities of graph learning to achieve fine-grained classification of low-quality labels. Experimental results on both real and synthetic datasets confirm that AGC can identify intrusions with high precision, while also being time-efficient in detection.
{"title":"Intrusion Detection for Internet of Things: An Anchor Graph Clustering Approach","authors":"Yixuan Wu;Long Zhang;Lin Yang;Feng Yang;Linru Ma;Zhoumin Lu;Wen Jiang","doi":"10.1109/TIFS.2025.3539100","DOIUrl":"10.1109/TIFS.2025.3539100","url":null,"abstract":"Intrusion detection systems are a crucial technique for securing the Internet of Things (IoT) from malicious attacks. Additionally, due to the continuous emergence of new vulnerabilities and unknown attack types, only a small number of attack samples in the IoT environments can be captured for analysis. In this work, we introduce an anchor graph clustering (AGC) method for intrusion detection to address the challenge of limited labeled samples in the IoT environments. AGC initially transforms the raw data into the embedding space to obtain more representative anchors. Then, AGC unifies anchor graph construction, anchor graph learning, and graph clustering into a unified framework, solving the resulting optimization problem through an iterative solution algorithm. Finally, AGC leverages the powerful analytical capabilities of graph learning to achieve fine-grained classification of low-quality labels. Experimental results on both real and synthetic datasets confirm that AGC can identify intrusions with high precision, while also being time-efficient in detection.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"1965-1980"},"PeriodicalIF":6.3,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143192086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-04DOI: 10.1109/TIFS.2025.3539089
Mingzhi Hu;Hongxia Wang
Coverless generative steganography is a highly secure method of information hiding. With the advent of the AI-generated content (AIGC) era, the widespread dissemination of generative content on the internet provides an excellent hiding environment for generative steganographic images. Generative steganographic images do not require the participation of carrier images, making existing steganalysis methods expired. However, there are currently no detection methods specifically targeting generative steganographic content. To address this gap, we propose a steganalysis method for generative steganographic images. Our approach focuses on the intrinsic differences between generative steganographic images and ordinary generative images. Through comparative analysis, we propose optimizing the detection model using mutual information estimation. We hypothesize about the distribution characteristics of steganographic signals and design a feature discrimination loss function to further guide the model’s optimization. In addition to designing a feature extraction network to extract features from different image regions, we also incorporate an image classification model pretrained on a large dataset to extract classification features for the final classification. Experimental results in various training and testing scenarios demonstrate that the proposed model not only possesses excellent detection capability but also exhibits reliable generalization compared to other models. Furthermore, we provide necessary descriptions and analysis to validate the rationale behind the network design.
{"title":"Mutual Information-Optimized Steganalysis for Generative Steganography","authors":"Mingzhi Hu;Hongxia Wang","doi":"10.1109/TIFS.2025.3539089","DOIUrl":"10.1109/TIFS.2025.3539089","url":null,"abstract":"Coverless generative steganography is a highly secure method of information hiding. With the advent of the AI-generated content (AIGC) era, the widespread dissemination of generative content on the internet provides an excellent hiding environment for generative steganographic images. Generative steganographic images do not require the participation of carrier images, making existing steganalysis methods expired. However, there are currently no detection methods specifically targeting generative steganographic content. To address this gap, we propose a steganalysis method for generative steganographic images. Our approach focuses on the intrinsic differences between generative steganographic images and ordinary generative images. Through comparative analysis, we propose optimizing the detection model using mutual information estimation. We hypothesize about the distribution characteristics of steganographic signals and design a feature discrimination loss function to further guide the model’s optimization. In addition to designing a feature extraction network to extract features from different image regions, we also incorporate an image classification model pretrained on a large dataset to extract classification features for the final classification. Experimental results in various training and testing scenarios demonstrate that the proposed model not only possesses excellent detection capability but also exhibits reliable generalization compared to other models. Furthermore, we provide necessary descriptions and analysis to validate the rationale behind the network design.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"1852-1865"},"PeriodicalIF":6.3,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143125175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-03DOI: 10.1109/tifs.2025.3537827
Ruichao Liang, Jing Chen, Cong Wu, Kun He, Yueming Wu, Ruochen Cao, Ruiying Du, Ziming Zhao, Yang Liu
{"title":"VULSEYE: Detect Smart Contract Vulnerabilities via Stateful Directed Graybox Fuzzing","authors":"Ruichao Liang, Jing Chen, Cong Wu, Kun He, Yueming Wu, Ruochen Cao, Ruiying Du, Ziming Zhao, Yang Liu","doi":"10.1109/tifs.2025.3537827","DOIUrl":"https://doi.org/10.1109/tifs.2025.3537827","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"61 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143083888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-03DOI: 10.1109/TIFS.2025.3537823
Xintao Pei;Yuling Chen;Yangyang Long;Haiwei Sang;Yun Luo
Cloud computing, as a promising service platform, has gained significant popularity in addressing emerging data privacy issues in applications such as machine learning and data mining. Researchers have proposed the verifiable computing that allows the cloud users to delegate their computation tasks to the cloud server. Then, the cloud server computes the cryptographic proofs that verify the correctness of the results, a process that is generally faster ompared to local manual computation. However, performing computation tasks or verifying the correctness of encrypted data, such as multivariate polynomial functions, remains a significant challenge. To solve this problem, we propose Einocchio: a verifiable computation scheme that combines the efficient Pinocchio system with homomorphic encryption, which allows the public verification of the computational results on the server side while ensuring data confidentiality and the results. Compared with the existing solutions, Einocchio does not reveal the client’s input. Furthermore, we extrapolate Einocchio by optimizing the Pinocchio’s quadratic arithmetic program component using a differential optimization method, which reduces the computational workload owing to the conversion from quadratic to linear complexity, thereby increasing the efficiency of the quadratic arithmetic program preprocessing stage. Security analysis demonstrates that Einocchio achieves IND-CPA security. Finally, the performance evaluation confirmed its effectiveness and suitability for cloud computing environments. Compared to the corresponding scheme based on Newton interpolation, Einocchio achieves a threefold greater computational efficiency, with the generation of interpolation polynomials for 50 data inputs occurring in a mere 0.31 ms, while simultaneously reducing the number of computations.
{"title":"Einocchio: Efficiently Outsourcing Polynomial Computation With Verifiable Computation and Optimized Newton Interpolation","authors":"Xintao Pei;Yuling Chen;Yangyang Long;Haiwei Sang;Yun Luo","doi":"10.1109/TIFS.2025.3537823","DOIUrl":"10.1109/TIFS.2025.3537823","url":null,"abstract":"Cloud computing, as a promising service platform, has gained significant popularity in addressing emerging data privacy issues in applications such as machine learning and data mining. Researchers have proposed the verifiable computing that allows the cloud users to delegate their computation tasks to the cloud server. Then, the cloud server computes the cryptographic proofs that verify the correctness of the results, a process that is generally faster ompared to local manual computation. However, performing computation tasks or verifying the correctness of encrypted data, such as multivariate polynomial functions, remains a significant challenge. To solve this problem, we propose Einocchio: a verifiable computation scheme that combines the efficient Pinocchio system with homomorphic encryption, which allows the public verification of the computational results on the server side while ensuring data confidentiality and the results. Compared with the existing solutions, Einocchio does not reveal the client’s input. Furthermore, we extrapolate Einocchio by optimizing the Pinocchio’s quadratic arithmetic program component using a differential optimization method, which reduces the computational workload owing to the conversion from quadratic to linear complexity, thereby increasing the efficiency of the quadratic arithmetic program preprocessing stage. Security analysis demonstrates that Einocchio achieves IND-CPA security. Finally, the performance evaluation confirmed its effectiveness and suitability for cloud computing environments. Compared to the corresponding scheme based on Newton interpolation, Einocchio achieves a threefold greater computational efficiency, with the generation of interpolation polynomials for 50 data inputs occurring in a mere 0.31 ms, while simultaneously reducing the number of computations.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"1981-1992"},"PeriodicalIF":6.3,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143083887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-30DOI: 10.1109/tifs.2025.3536277
Gokularam Muthukrishnan, Sheetal Kalyani
{"title":"Differential Privacy with Higher Utility by Exploiting Coordinate-wise Disparity: Laplace Mechanism Can Beat Gaussian in High Dimensions","authors":"Gokularam Muthukrishnan, Sheetal Kalyani","doi":"10.1109/tifs.2025.3536277","DOIUrl":"https://doi.org/10.1109/tifs.2025.3536277","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"33 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-30DOI: 10.1109/TIFS.2025.3536613
Yongxiang Li;Yuan Sun;Yang Qin;Dezhong Peng;Xi Peng;Peng Hu
Unsupervised visible-infrared person re-identification (UVI-ReID) aims at retrieving pedestrian images of the same individual across distinct modalities, presenting challenges due to the inherent heterogeneity gap and the absence of cost-prohibitive annotations. Although existing methods employ self-training with clustering-generated pseudo-labels to bridge this gap, they always implicitly assume that these pseudo-labels are predicted correctly. In practice, however, this presumption is impossible to satisfy due to the difficulty of training a perfect model let alone without any ground truths, resulting in pseudo-labeling errors. Based on the observation, this study introduces a new learning paradigm for UVI-ReID considering Pseudo-Label Noise (PLN), which encompasses three challenges: noise overfitting, error accumulation, and noisy cluster correspondence. To conquer these challenges, we propose a novel robust duality learning framework (RoDE) for UVI-ReID to mitigate the adverse impact of noisy pseudo-labels. Specifically, for noise overfitting, we propose a novel Robust Adaptive Learning mechanism (RAL) to dynamically prioritize clean samples while deprioritizing noisy ones, thus avoiding overemphasizing noise. To circumvent error accumulation of self-training, where the model tends to confirm its mistakes, RoDE alternately trains dual distinct models using pseudo-labels predicted by their counterparts, thereby maintaining diversity and avoiding collapse into noise. However, this will lead to cross-cluster misalignment between the two distinct models, not to mention the misalignment between different modalities, resulting in dual noisy cluster correspondence and thus difficult to optimize. To address this issue, a Cluster Consistency Matching mechanism (CCM) is presented to ensure reliable alignment across distinct modalities as well as across different models by leveraging cross-cluster similarities. Extensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed RoDE.
{"title":"Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification","authors":"Yongxiang Li;Yuan Sun;Yang Qin;Dezhong Peng;Xi Peng;Peng Hu","doi":"10.1109/TIFS.2025.3536613","DOIUrl":"10.1109/TIFS.2025.3536613","url":null,"abstract":"Unsupervised visible-infrared person re-identification (UVI-ReID) aims at retrieving pedestrian images of the same individual across distinct modalities, presenting challenges due to the inherent heterogeneity gap and the absence of cost-prohibitive annotations. Although existing methods employ self-training with clustering-generated pseudo-labels to bridge this gap, they always implicitly assume that these pseudo-labels are predicted correctly. In practice, however, this presumption is impossible to satisfy due to the difficulty of training a perfect model let alone without any ground truths, resulting in pseudo-labeling errors. Based on the observation, this study introduces a new learning paradigm for UVI-ReID considering Pseudo-Label Noise (PLN), which encompasses three challenges: noise overfitting, error accumulation, and noisy cluster correspondence. To conquer these challenges, we propose a novel robust duality learning framework (RoDE) for UVI-ReID to mitigate the adverse impact of noisy pseudo-labels. Specifically, for noise overfitting, we propose a novel Robust Adaptive Learning mechanism (RAL) to dynamically prioritize clean samples while deprioritizing noisy ones, thus avoiding overemphasizing noise. To circumvent error accumulation of self-training, where the model tends to confirm its mistakes, RoDE alternately trains dual distinct models using pseudo-labels predicted by their counterparts, thereby maintaining diversity and avoiding collapse into noise. However, this will lead to cross-cluster misalignment between the two distinct models, not to mention the misalignment between different modalities, resulting in dual noisy cluster correspondence and thus difficult to optimize. To address this issue, a Cluster Consistency Matching mechanism (CCM) is presented to ensure reliable alignment across distinct modalities as well as across different models by leveraging cross-cluster similarities. Extensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed RoDE.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"1937-1948"},"PeriodicalIF":6.3,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-30DOI: 10.1109/TIFS.2025.3536611
Bo Yang;Hengwei Zhang;Jindong Wang;Yulong Yang;Chenhao Lin;Chao Shen;Zhengyu Zhao
Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing transferability is to keep only the optimal adversarial example from all those obtained in the optimization pipeline. In this paper, for the first time, we revisit this convention and demonstrate that those discarded, sub-optimal adversarial examples can be reused to boost transferability. Specifically, we propose “Adversarial Example Soups” (AES), with AES-tune for averaging discarded adversarial examples in hyperparameter tuning and AES-rand for stability testing. In addition, our AES is inspired by “model soups”, which averages weights of multiple fine-tuned models for improved accuracy without increasing inference time. Extensive experiments validate the global effectiveness of our AES, boosting 10 state-of-the-art transfer attacks and their combinations by up to 13% against 10 diverse (defensive) target models. We also show the possibility of generalizing AES to other types, e.g., directly averaging multiple in-the-wild adversarial examples that yield comparable success. A promising byproduct of AES is the improved stealthiness of adversarial examples since the perturbation variances are naturally reduced.
{"title":"Adversarial Example Soups: Improving Transferability and Stealthiness for Free","authors":"Bo Yang;Hengwei Zhang;Jindong Wang;Yulong Yang;Chenhao Lin;Chao Shen;Zhengyu Zhao","doi":"10.1109/TIFS.2025.3536611","DOIUrl":"10.1109/TIFS.2025.3536611","url":null,"abstract":"Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing transferability is to keep only the optimal adversarial example from all those obtained in the optimization pipeline. In this paper, for the first time, we revisit this convention and demonstrate that those discarded, sub-optimal adversarial examples can be reused to boost transferability. Specifically, we propose “Adversarial Example Soups” (AES), with AES-tune for averaging discarded adversarial examples in hyperparameter tuning and AES-rand for stability testing. In addition, our AES is inspired by “model soups”, which averages weights of multiple fine-tuned models for improved accuracy without increasing inference time. Extensive experiments validate the global effectiveness of our AES, boosting 10 state-of-the-art transfer attacks and their combinations by up to 13% against 10 diverse (defensive) target models. We also show the possibility of generalizing AES to other types, e.g., directly averaging multiple in-the-wild adversarial examples that yield comparable success. A promising byproduct of AES is the improved stealthiness of adversarial examples since the perturbation variances are naturally reduced.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"20 ","pages":"1882-1894"},"PeriodicalIF":6.3,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-30DOI: 10.1109/tifs.2025.3536777
Jingjing Xue, Sheng Sun, Min Liu, Qi Li, Ke Xu
{"title":"Enhancing Federated Learning Robustness using Locally Benignity-Assessable Bayesian Dropout","authors":"Jingjing Xue, Sheng Sun, Min Liu, Qi Li, Ke Xu","doi":"10.1109/tifs.2025.3536777","DOIUrl":"https://doi.org/10.1109/tifs.2025.3536777","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"77 3 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","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：