標(biāo)題: Titlebook: Attacks, Defenses and Testing for Deep Learning; Jinyin Chen,Ximin Zhang,Haibin Zheng Book 2024 The Editor(s) (if applicable) and The Auth [打印本頁(yè)] 作者: risky-drinking 時(shí)間: 2025-3-21 19:32
書目名稱Attacks, Defenses and Testing for Deep Learning影響因子(影響力)
書目名稱Attacks, Defenses and Testing for Deep Learning影響因子(影響力)學(xué)科排名
書目名稱Attacks, Defenses and Testing for Deep Learning網(wǎng)絡(luò)公開度
書目名稱Attacks, Defenses and Testing for Deep Learning網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Attacks, Defenses and Testing for Deep Learning被引頻次
書目名稱Attacks, Defenses and Testing for Deep Learning被引頻次學(xué)科排名
書目名稱Attacks, Defenses and Testing for Deep Learning年度引用
書目名稱Attacks, Defenses and Testing for Deep Learning年度引用學(xué)科排名
書目名稱Attacks, Defenses and Testing for Deep Learning讀者反饋
書目名稱Attacks, Defenses and Testing for Deep Learning讀者反饋學(xué)科排名
作者: Debark 時(shí)間: 2025-3-21 23:08 作者: 采納 時(shí)間: 2025-3-22 01:28 作者: 生存環(huán)境 時(shí)間: 2025-3-22 07:42 作者: SEEK 時(shí)間: 2025-3-22 10:39
Principles of Courtroom Testimonyllected from users, GNN may struggle to deliver optimal performance due to the lack of rich features and complete adjacent relationships. To address this challenge, a solution called vertical federated learning (VFL) has been proposed, which aims to protect local data privacy by training a global mo作者: 燈泡 時(shí)間: 2025-3-22 14:14 作者: 遺忘 時(shí)間: 2025-3-22 17:44 作者: 哄騙 時(shí)間: 2025-3-22 21:58 作者: engagement 時(shí)間: 2025-3-23 04:17
Santiago Vergara-Pineda,Irma Aviles-Carrillo as it greatly impacts the prediction performance of most DLP methods, making them highly dependent on it. Backdoor attacks are used to manipulate DLP methods to cause incorrect predictions by the malicious training data, i.e., generating a trigger in the form of a subgraph sequence and embedding it作者: 有法律效應(yīng) 時(shí)間: 2025-3-23 06:55 作者: 泛濫 時(shí)間: 2025-3-23 13:44 作者: 宣誓書 時(shí)間: 2025-3-23 16:08
Mitigation of Climatic Warming in Forestryes have shown that deep neural networks (DNNs) are always vulnerable to adversarial attacks. In order to identify the commonalities between various attacks, we compare the variation between clean and adversarial examples through model-hiding feature visualization methods (i.e., heatmaps), as adversa作者: 做作 時(shí)間: 2025-3-23 21:39 作者: 含糊其辭 時(shí)間: 2025-3-24 00:46 作者: Negotiate 時(shí)間: 2025-3-24 05:35 作者: delusion 時(shí)間: 2025-3-24 08:59
Soil Management Impacts on Soil Carbon its excellent performance and significant profits, it has been applied to a wide range of practical areas. . has become a major issue. It is possible that FL could benefit from the existing property rights protection methods in centralized scenarios, such as watermark embedding and model fingerprin作者: 重疊 時(shí)間: 2025-3-24 11:32
Soil Management Impacts on Soil Carbontypically suffer from the large-scale data collection challenge of centralized training, i.e., some institutions own some of the features of the data while they need to protect the privacy of the local data. Therefore, Vertical Federated Graph Learning (VFGL) is gaining popularity as a framework tha作者: 膽大 時(shí)間: 2025-3-24 15:03
Forests Are Key to Climate Mitigation,ared global model. Unluckily, by uploading a carefully crafted updated model, a malicious client can insert a backdoor into the global model during federated learning training. Many secure aggregation policies and robust training protocols have been proposed to protect against backdoor attacks in FL作者: HOWL 時(shí)間: 2025-3-24 20:43
https://doi.org/10.1007/978-981-97-0425-5Deep Learning; Deep Neural Network; Adversarial Attack; Adversarial Defense; Poisoning Attack; Poisoning 作者: 變形詞 時(shí)間: 2025-3-25 00:52
978-981-97-0427-9The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapor作者: 障礙物 時(shí)間: 2025-3-25 07:07
Jinyin Chen,Ximin Zhang,Haibin ZhengThe security problems of different data modes, different model structures and different tasks are fully considered.The attack problems are comprehensively studied, and the system flow of the attack-de作者: JOG 時(shí)間: 2025-3-25 08:38
http://image.papertrans.cn/b/image/164877.jpg作者: 事與愿違 時(shí)間: 2025-3-25 13:22 作者: CHOKE 時(shí)間: 2025-3-25 19:16 作者: novelty 時(shí)間: 2025-3-25 20:00
Adversarial Attacks on?GNN-Based Vertical Federated Learningllected from users, GNN may struggle to deliver optimal performance due to the lack of rich features and complete adjacent relationships. To address this challenge, a solution called vertical federated learning (VFL) has been proposed, which aims to protect local data privacy by training a global mo作者: Fibrinogen 時(shí)間: 2025-3-26 01:50
A Novel DNN Object Contour Attack on?Image Recognitioneptible to adversarial examples. Currently, the primary focus of research on generating adversarial examples is to improve the attack success rate (ASR) while minimizing the perturbation size. Through the visualization of heatmaps, previous studies have identified that the feature extraction capabil作者: 群居動(dòng)物 時(shí)間: 2025-3-26 04:58
Query-Efficient Adversarial Attack Against Vertical Federated Graph Learninga. However, the performance of GNN is limited by distributing data silos. Vertical federated learning (VFL) enables GNN to process distributed graph-structured data. While vertical federated graph learning (VFGL) has experienced prosperous development, its robustness against adversarial attacks has 作者: Working-Memory 時(shí)間: 2025-3-26 08:30
Targeted Label Adversarial Attack on?Graph Embedding The increasing interest in graph mining has led to the development of attack methods on graph embedding. Most of these attack methods aim to generate perturbations that maximize the deviation of prediction confidence. However, they often struggle to accurately misclassify instances into the desired作者: Manifest 時(shí)間: 2025-3-26 13:15 作者: 灰姑娘 時(shí)間: 2025-3-26 19:37 作者: 確定的事 時(shí)間: 2025-3-26 22:29 作者: Lipohypertrophy 時(shí)間: 2025-3-27 02:59 作者: 胖人手藝好 時(shí)間: 2025-3-27 05:48
Neuron-Level Inverse Perturbation Against Adversarial Attackson, especially when deployed in security-critical domains. Numerous defense methods, including reactive and proactive ones, have been proposed for model robustness improvement. The former ones, such as conducting transformations to remove perturbations, usually fail to handle large perturbations via作者: 少量 時(shí)間: 2025-3-27 12:12 作者: 光亮 時(shí)間: 2025-3-27 16:04
Defense Against Free-Rider Attack from?the?Weight Evolving Frequencyuted machine learning. Although federated learning has gained an unprecedented success in data privacy preservation, its frailty of vulnerability to “free-rider” attacks attracts increasing attention. A number of defenses against free-rider attacks have been proposed for FL. Nevertheless, these meth作者: legislate 時(shí)間: 2025-3-27 19:40
An Effective Model Copyright Protection for?Federated Learning its excellent performance and significant profits, it has been applied to a wide range of practical areas. . has become a major issue. It is possible that FL could benefit from the existing property rights protection methods in centralized scenarios, such as watermark embedding and model fingerprin作者: 統(tǒng)治人類 時(shí)間: 2025-3-27 22:40 作者: 忍受 時(shí)間: 2025-3-28 05:32
Using Adversarial Examples to against Backdoor Attack in Federated Learningared global model. Unluckily, by uploading a carefully crafted updated model, a malicious client can insert a backdoor into the global model during federated learning training. Many secure aggregation policies and robust training protocols have been proposed to protect against backdoor attacks in FL作者: 物種起源 時(shí)間: 2025-3-28 07:14 作者: Predigest 時(shí)間: 2025-3-28 12:10 作者: 頌揚(yáng)本人 時(shí)間: 2025-3-28 15:43
Adversarial Attacks on?GNN-Based Vertical Federated Learningon the noise-enhanced global node embeddings, leveraging privacy leakage and the gradient of pairwise nodes. Our approach begins by stealing the global node embeddings and constructing a shadow model of the server for the attack generator. Next, we introduce noise into the node embeddings to confuse作者: recede 時(shí)間: 2025-3-28 19:17 作者: chassis 時(shí)間: 2025-3-29 01:13
Query-Efficient Adversarial Attack Against Vertical Federated Graph Learningd using the manipulated data to imitate the behavior of the server model in VFGL. Consequently, the shadow model can significantly boost the success rate of centralized attacks with minimal queries. Multiple tests conducted on four real-world benchmarks show that our method can enhance the performan作者: wangle 時(shí)間: 2025-3-29 06:56 作者: 冷漠 時(shí)間: 2025-3-29 09:21
Backdoor Attack on?Dynamic Link Predictionet. This process helps reduce the size of the triggers and enhances the concealment of the attack. Experimental results demonstrate that our method successfully launches backdoor attacks on several state-of-the-art DLP models, achieving a success rate exceeding 90%.作者: Measured 時(shí)間: 2025-3-29 15:06
Attention Mechanism-Based Adversarial Attack Against DRLdversarial state. DQN is one of the state-of-the-art DRL models and is used as the target model to train the Flappybird gaming environment to assure continuous operation and high success rates. We performed comprehensive attack experiments on DQN and examined its attack performance in terms of rewar作者: 縮短 時(shí)間: 2025-3-29 17:46 作者: clarify 時(shí)間: 2025-3-29 20:14 作者: 壓艙物 時(shí)間: 2025-3-30 03:14 作者: garrulous 時(shí)間: 2025-3-30 07:26
Adaptive Channel Transformation-Based Detector for?Adversarial Attacksn instances but also can recognize the types of attacks, such as white-box attacks and black-box attacks. In order to validate the detection efficiency of our method, we conduct comprehensive experiments on MNIST, CIFAR10, and ImageNet datasets. With 99.05% and 98.8% detection rates on the MNIST and作者: 高歌 時(shí)間: 2025-3-30 10:03 作者: 耕種 時(shí)間: 2025-3-30 12:30 作者: blight 時(shí)間: 2025-3-30 18:31 作者: Obituary 時(shí)間: 2025-3-30 21:16 作者: 生命層 時(shí)間: 2025-3-31 03:24 作者: 小教堂 時(shí)間: 2025-3-31 06:31
The Negative Medicolegal Autopsyut the attack. It is shown by extensive experiments that our method can achieve a state-of-the-art attack success rate, as high as 91.74%, with only 7% poisoned samples on publicly available datasets LFW and CASIA. Furthermore, we have experimented with high-performance defense algorithms such as au作者: 不連貫 時(shí)間: 2025-3-31 11:21
Principles of Courtroom Testimonyon the noise-enhanced global node embeddings, leveraging privacy leakage and the gradient of pairwise nodes. Our approach begins by stealing the global node embeddings and constructing a shadow model of the server for the attack generator. Next, we introduce noise into the node embeddings to confuse
