The academic intelligence of large language models (LLMs) has made remarkable progress in recent times, but their social intelligence performance remains unclear. Inspired by established human social intelligence fram...
详细信息
In recent years, Android application privacy leaking issues frequently occur, with the results that privacy leakage detection becomes a critical role in app market security review, and numerous mobile apps have been r...
详细信息
While large visual models (LVM) demonstrated significant potential in image understanding, due to the application of large-scale pre-training, the Segment Anything Model (SAM) has also achieved great success in the fi...
详细信息
Merging various task-specific Transformer-based vision models trained on different tasks into a unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have proven to be...
详细信息
Merging various task-specific Transformer-based vision models trained on different tasks into a unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have proven to be both effective and scalable. Existing methods have primarily focused on seeking a static optimal solution within the original model parameter space. A notable challenge is mitigating the interference between parameters of different models, which can substantially deteriorate performance. In this paper, we propose to merge most of the parameters while upscaling the MLP of the Transformer layers to a weight-ensembling mixture of experts (MoE) module, which can dynamically integrate shared and task-specific knowledge based on the input, thereby providing a more flexible solution that can adapt to the specific needs of each instance. Our key insight is that by identifying and separating shared knowledge and task-specific knowledge, and then dynamically integrating them, we can mitigate the parameter interference problem to a great extent. We conduct the conventional multi-task model merging experiments and evaluate the generalization and robustness of our method. The results demonstrate the effectiveness and provide a comprehensive understanding of our method. Copyright 2024 by the author(s)
software reuse realizes the sharing of software resources, and component-based reuse is the main form of software reuse. The classification, storage, retrieval, and release of a large number of component resources req...
详细信息
Long-term time series forecasting is a long-standing challenge in various applications. A central issue in time series forecasting is that methods should expressively capture long-term dependency. Furthermore, time se...
详细信息
During the last decade, deep learning has played a significant role in improving text classification which is widely applied in question answering systems, comment extraction, sentiment analysis, etc. Considering that...
详细信息
This paper proposes a novel ETC-MTCTR, which is designed to enable more accurate, versatile and efficient traffic classification in the context of multi-scenario, low-resource encrypted traffic. Through three modules ...
详细信息
ISBN:
(数字)9798350368369
ISBN:
(纸本)9798350368376
This paper proposes a novel ETC-MTCTR, which is designed to enable more accurate, versatile and efficient traffic classification in the context of multi-scenario, low-resource encrypted traffic. Through three modules of Datagram Token conversion, pretraining and fine-tuning, the method uses large-scale unlabeled encrypted traffic for pretraining, mining and learning the traffic context and transmission relationship of encrypted traffic classification tasks, so that a small number of labeled data samples can be effectively used in the fine-tuning stage. Significantly improve the performance of the model on specific downstream classification tasks, enhance the accuracy, adaptability and robustness of the model in diverse environments, limited resources and new encryption security protocols, and realize efficient encryption traffic classification in multi-scenario and low-resource background. The results show that ETC-MTCTR achieves the best performance on three tasks: encryption malware classification, VPN encrypted traffic classification, and TLS 1.3 encryption application classification. Its F1 score is improved by 0.22% in the classification task of encrypted malware, 1.4% in the classification task of VPN encrypted traffic App, 4.56% in the classification task of VPN encrypted traffic Service, and 9.89% in the classification task of TLS 1.3 encrypted application, which is significantly better than other comparison methods.
Despite tons of advanced classification models that have recently been developed for the land cover mapping task,the monotonicity of a single remote sensing data source,such as only using hyperspectral data or multisp...
详细信息
Despite tons of advanced classification models that have recently been developed for the land cover mapping task,the monotonicity of a single remote sensing data source,such as only using hyperspectral data or multispectral data,hinders the classification accuracy from being further improved and tends to meet the performance *** this reason,we develop a novel superpixel-based subspace learning model,called Supace,by jointly learning multimodal feature representations from HS and MS superpixels for more accurate LCC *** can learn a common subspace across multimodal RS data,where the diverse and complementary information from different modalities can be better combined,being capable of enhancing the discriminative ability of to-be-learned features in a more effective *** better capture semantic information of objects in the feature learning process,superpixels that beyond pixels are regarded as the study object in our Supace for *** experiments have been conducted on two popular hyperspectral and multispectral datasets,demonstrating the superiority of the proposed Supace in the land cover classification task compared with several well-known baselines related to multimodal remote sensing image feature learning.
This paper investigates the gender gap in South Africa’s cybersecurity sector and its effects on both the sector and the nation’s economic growth. There is a significant shortage of skilled workers in the sector, an...
This paper investigates the gender gap in South Africa’s cybersecurity sector and its effects on both the sector and the nation’s economic growth. There is a significant shortage of skilled workers in the sector, and women are notably underrepresented. The main research question examines how the gender gap affects the industry’s development, innovation, and national security posture, emphasizing the importance of utilizing the nation’s talent pool to its fullest capacity to combat the evolving cyber threats. Insights and perspectives on the gender disparity in the cybersecurity sector were gathered through a questionnaire circulated amongst cybersecurity professionals and academics. These participants were chosen due to their knowledge and direct engagement in the subject, which offers valuable insights into the obstacles that women encounter in their workplace. The study highlights a number of problems, including gender stereotypes, a lack of access to education and training, and a non-inclusive workplace culture, that contribute to the gender gap. The paper makes the case that in order to solve these problems and advance diversity and inclusivity in the workplace, all stakeholders must work together to close the gender gap. In order to overcome the gender gap in cybersecurity in South Africa, the study suggests special programs aimed at expanding access to education and training opportunities, promoting gender diversity and inclusivity, and creating a more hospitable and equal work environment. This will boost the country's economic growth and strengthen security against cyberattacks.
暂无评论