This paper investigates the limitations of the widely adopted softmax cross-entropy loss in incremental learning problems. Specifically, we highlight how the shift-invariant property of this loss function can lead to ...
详细信息
Sparse principal component analysis (PCA) improves interpretability of the classic PCA by introducing sparsity into the dimension-reduction process. Optimization models for sparse PCA, however, are generally non-conve...
详细信息
Lack of transparency in deep learning models makes them vulnerable to backdoor attack, which can cause severe security consequences. For a backdoored model, the specific inputs can trigger misclassification rules whil...
详细信息
ISBN:
(纸本)9781728181059
Lack of transparency in deep learning models makes them vulnerable to backdoor attack, which can cause severe security consequences. For a backdoored model, the specific inputs can trigger misclassification rules while it performs normal behaviors on clean data. Existing backdoor attacks usually generate poisoned data by adding an obvious trigger to the original data and mislabeling them, which suffers from poor invisibility and hence can be easily detected. In this paper, we propose Stand-in Backdoor, a more stealthy and powerful backdoor attack, which can completely hide the trigger while maintaining correct labels of poisoned data. Specifically, we design a novel optimization strategy to transform triggers into imperceptible perturbation in the feature space. Furthermore, utilizing the transferability of feature perturbation, we fine-tune the victim model with well-constructed poisoned data that are correctly labeled. Extensive experiments conducted on various image classification tasks demonstrate that our attack outperforms the state-of-the-art work in terms of backdoor stealth and attack performance, without sacrificing the model's utility.
The semantic segmentation task faces the bottleneck of high manual annotation costs. Domain adaptive learning provides an effective solution through inter domain knowledge transfer. However, existing domain adaptive s...
详细信息
The semantic segmentation task faces the bottleneck of high manual annotation costs. Domain adaptive learning provides an effective solution through inter domain knowledge transfer. However, existing domain adaptive semantic segmentation tasks face the situation of category asymmetry between scenes when dealing with complex scenes. Existing methods lack handling of class imbalance in the prediction process. In domain adaptive semantic segmentation tasks, class imbalance limits the performance of inter domain transfer. Our work focuses on the impact of category distribution on domain adaptive semantic segmentation tasks in image pairs. Inspired by long tail learning, we divided categories into head, middle, and tail categories, and designed effective strategies to enhance the contribution of tail categories in domain adaptation tasks. We introduce the concept of category rebalancing into domain adaptive image matching, and our method is lightweight and effective, proving its effectiveness on general datasets.
g-C3N4/TiO2 composite has excellent photoelectric properties and is considered as a good carrier of nanoparticles. A novel composite of nZVI-g-C3N4/TiO2 was successfully synthesized through in-situ growth nZVI on the ...
详细信息
The traditional domain adaptation task is not sufficient in mining inter domain image context. We propose a solution from the perspective of image semantic level retrieval. Image semantic level retrieval is based on t...
详细信息
The traditional domain adaptation task is not sufficient in mining inter domain image context. We propose a solution from the perspective of image semantic level retrieval. Image semantic level retrieval is based on the high-level semantics of images, retrieving the similarity or correspondence between images in terms of content and scene between domains. Our work focuses on the meaning, structure, and contextual information expressed by the target image, and retrieves the most relevant image from the source domain to improve the accuracy of domain adaptation. Furthermore, in response to the negative transfer brought about by image retrieval, we will introduce a category level weight adjustment module to further improve the accuracy of semantic level retrieval and weaken the negative impact caused by low precision categories. Finally, we demonstrated the effectiveness of semantic level image retrieval through experiments.
The emergence of sixth-generation and beyond communication systems is expected to fundamentally transform digital experiences through introducing unparalleled levels of intelligence, efficiency, and connectivity. A pr...
详细信息
Randomized controlled trials(RCTs)provide optimal evidence of the effectiveness and safety of a new drug,a new medical device,or a new therapeutic strategy with the necessary scientific design[1].Traditional electroni...
详细信息
Randomized controlled trials(RCTs)provide optimal evidence of the effectiveness and safety of a new drug,a new medical device,or a new therapeutic strategy with the necessary scientific design[1].Traditional electronic data collection(EDC)systems for clinical trials primarily focus on data entry,validation,and compliance ***,their reliance on centralized architectures introduces vulnerabilities in data security and integrity。
Multi-Constrained Graph Pattern Matching (MC-GPM) aims to match a pattern graph with multiple attribute constraints on its nodes and edges, and has garnered significant interest in various fields, including social-bas...
Multi-Constrained Graph Pattern Matching (MC-GPM) aims to match a pattern graph with multiple attribute constraints on its nodes and edges, and has garnered significant interest in various fields, including social-based e-commerce and trust-based group discovery. However, the existing MC-GPM methods do not consider situations where the number of each node in the pattern graph needs to be fixed, such as finding experts group with expert quantities and relations specified. In this paper, a Multi-Constrained Strong Simulation with the Fixed Number of Nodes (MCSS-FNN) matching model is proposed, and then a Trust-oriented Optimal Multi-constrained Path (TOMP) matching algorithm is designed for solving it. Additionally, two heuristic optimization strategies are designed, one for combinatorial testing and the other for edge matching, to enhance the efficiency of the TOMP algorithm. Empirical experiments are conducted on four real social network datasets, and the results demonstrate the effectiveness and efficiency of the proposed algorithm and optimization strategies.
Group signature is a useful cryptographic primitive that allows a message to be signed by a user on behalf of a group which is managed by some trusted authority, namely the group manager. However, group signature sche...
详细信息
暂无评论