Target tracking is an essential task in contemporary computer vision applications.However,its effectiveness is susceptible to model drift,due to the different appearances of targets,which often compromises tracking ro...Target tracking is an essential task in contemporary computer vision applications.However,its effectiveness is susceptible to model drift,due to the different appearances of targets,which often compromises tracking robustness and precision.In this paper,a universally applicable method based on correlation filters is introduced to mitigate model drift in complex scenarios.It employs temporal-confidence samples as a priori to guide the model update process and ensure its precision and consistency over a long period.An improved update mechanism based on the peak side-lobe to peak correlation energy(PSPCE)criterion is proposed,which selects high-confidence samples along the temporal dimension to update temporal-confidence samples.Extensive experiments on various benchmarks demonstrate that the proposed method achieves a competitive performance compared with the state-of-the-art methods.Especially when the target appearance changes significantly,our method is more robust and can achieve a balance between precision and speed.Specifically,on the object tracking benchmark(OTB-100)dataset,compared to the baseline,the tracking precision of our model improves by 8.8%,8.8%,5.1%,5.6%,and 6.9%for background clutter,deformation,occlusion,rotation,and illumination variation,respectively.The results indicate that this proposed method can significantly enhance the robustness and precision of target tracking in dynamic and challenging environments,offering a reliable solution for applications such as real-time monitoring,autonomous driving,and precision guidance.展开更多
High-confidence computing relies on trusted instructional set architecture,sealed kernels,and secure operating systems.Cloud computing depends on trusted systems for virtualization tasks.Branch predictions and pipelin...High-confidence computing relies on trusted instructional set architecture,sealed kernels,and secure operating systems.Cloud computing depends on trusted systems for virtualization tasks.Branch predictions and pipelines are essential in improving performance of a CPU/GPU.But Spectre and Meltdown make modern processors vulnerable to be exploited.Disabling the prediction and pipeline is definitely not a good solution.On the other hand,current software patches can only address non-essential issues around Meltdown.This paper introduces a holistic approach in trusted computer architecture design and emulation.展开更多
Fusarium head blight(FHB) is a global wheat disease that devastates wheat production. Resistance to FHB spread within a wheat spike(type Ⅱ resistance) and to mycotoxin accumulation in infected kernel(type Ⅲ resistan...Fusarium head blight(FHB) is a global wheat disease that devastates wheat production. Resistance to FHB spread within a wheat spike(type Ⅱ resistance) and to mycotoxin accumulation in infected kernel(type Ⅲ resistance) are the two main types of resistance. Of hundreds of QTL that have been reported, only a few can be used in wheat breeding because most show minor and/or inconsistent effects in different genetic backgrounds. We describe a new strategy for identifying robust and reliable meta-QTL(mQTL)that can be used for improvement of wheat FHB resistance. It involves integration of mQTL analysis with mQTL physical mapping and identification of single-copy markers and candidate genes. Using metaanalysis, we consolidated 625 original QTL from 113 publications into 118 genetic map-based mQTL(gmQTL). These gmQTL were further located on the Chinese Spring reference sequence map. Finally, 77 high-confidence mQTL(hcmQTL) were selected from the reference sequence-based mQTL(smQTL).Locus-specific single nucleotide polymorphism(SNP) and simple sequence repeat(SSR) markers and17 genes responsive to FHB were then identified in the hcmQTL intervals by combined analysis of transcriptomic and proteomic data. This work may lead to a comprehensive molecular breeding platform for improving wheat resistance to FHB.展开更多
The federated learning framework builds a deep learning model collaboratively by a group of connected devices via only sharing local parameter updates to the central parameter server.Nonetheless,the lack of transparen...The federated learning framework builds a deep learning model collaboratively by a group of connected devices via only sharing local parameter updates to the central parameter server.Nonetheless,the lack of transparency in the local data resource makes it prone to adversarial federated attacks,which have shown increasing ability to reduce learning performance.Existing research efforts either focus on the single-party attack with impractical perfect knowledge setting and limited stealthy ability or the random attack that has no control on attack effects.In this paper,we investigate a new multi-party adversarial attack with the imperfect knowledge of the target system.Controlled by an adversary,a number of compromised devices collaboratively launch targeted model poisoning attacks,intending to misclassify the targeted samples while maintaining stealthy under different de-tection strategies.Specifically,the compromised devices jointly minimize the loss function of model training in different scenarios.To overcome the update scaling problem,we develop a new boosting strategy by introducing two stealthy metrics.Via experimental results,we show that under both perfect knowledge and limited knowl-edge settings,the multi-party attack is capable of successfully evading detection strategies while guaranteeing the convergence.We also demonstrate that the learned model achieves the high accuracy on the targeted samples,which confirms the significant impact of the multi-party attack on federated learning systems.展开更多
基金supported by the Natural Science Foundation of Sichuan Province of China under Grant No.2025ZNSFSC0522partially supported by the National Natural Science Foundation of China under Grants No.61775030 and No.61571096.
文摘Target tracking is an essential task in contemporary computer vision applications.However,its effectiveness is susceptible to model drift,due to the different appearances of targets,which often compromises tracking robustness and precision.In this paper,a universally applicable method based on correlation filters is introduced to mitigate model drift in complex scenarios.It employs temporal-confidence samples as a priori to guide the model update process and ensure its precision and consistency over a long period.An improved update mechanism based on the peak side-lobe to peak correlation energy(PSPCE)criterion is proposed,which selects high-confidence samples along the temporal dimension to update temporal-confidence samples.Extensive experiments on various benchmarks demonstrate that the proposed method achieves a competitive performance compared with the state-of-the-art methods.Especially when the target appearance changes significantly,our method is more robust and can achieve a balance between precision and speed.Specifically,on the object tracking benchmark(OTB-100)dataset,compared to the baseline,the tracking precision of our model improves by 8.8%,8.8%,5.1%,5.6%,and 6.9%for background clutter,deformation,occlusion,rotation,and illumination variation,respectively.The results indicate that this proposed method can significantly enhance the robustness and precision of target tracking in dynamic and challenging environments,offering a reliable solution for applications such as real-time monitoring,autonomous driving,and precision guidance.
文摘High-confidence computing relies on trusted instructional set architecture,sealed kernels,and secure operating systems.Cloud computing depends on trusted systems for virtualization tasks.Branch predictions and pipelines are essential in improving performance of a CPU/GPU.But Spectre and Meltdown make modern processors vulnerable to be exploited.Disabling the prediction and pipeline is definitely not a good solution.On the other hand,current software patches can only address non-essential issues around Meltdown.This paper introduces a holistic approach in trusted computer architecture design and emulation.
基金supported by the National Key R&D Program,Intergovernmental Key Items for International Scientific and Technological Innovation Cooperation(2018YFE0107700)the National Natural Science Foundation of China(31771772)+2 种基金the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX19_2109)the National Key R&D Program for Breeding of Top-seven Crops(2017YFD0100801)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)。
文摘Fusarium head blight(FHB) is a global wheat disease that devastates wheat production. Resistance to FHB spread within a wheat spike(type Ⅱ resistance) and to mycotoxin accumulation in infected kernel(type Ⅲ resistance) are the two main types of resistance. Of hundreds of QTL that have been reported, only a few can be used in wheat breeding because most show minor and/or inconsistent effects in different genetic backgrounds. We describe a new strategy for identifying robust and reliable meta-QTL(mQTL)that can be used for improvement of wheat FHB resistance. It involves integration of mQTL analysis with mQTL physical mapping and identification of single-copy markers and candidate genes. Using metaanalysis, we consolidated 625 original QTL from 113 publications into 118 genetic map-based mQTL(gmQTL). These gmQTL were further located on the Chinese Spring reference sequence map. Finally, 77 high-confidence mQTL(hcmQTL) were selected from the reference sequence-based mQTL(smQTL).Locus-specific single nucleotide polymorphism(SNP) and simple sequence repeat(SSR) markers and17 genes responsive to FHB were then identified in the hcmQTL intervals by combined analysis of transcriptomic and proteomic data. This work may lead to a comprehensive molecular breeding platform for improving wheat resistance to FHB.
文摘The federated learning framework builds a deep learning model collaboratively by a group of connected devices via only sharing local parameter updates to the central parameter server.Nonetheless,the lack of transparency in the local data resource makes it prone to adversarial federated attacks,which have shown increasing ability to reduce learning performance.Existing research efforts either focus on the single-party attack with impractical perfect knowledge setting and limited stealthy ability or the random attack that has no control on attack effects.In this paper,we investigate a new multi-party adversarial attack with the imperfect knowledge of the target system.Controlled by an adversary,a number of compromised devices collaboratively launch targeted model poisoning attacks,intending to misclassify the targeted samples while maintaining stealthy under different de-tection strategies.Specifically,the compromised devices jointly minimize the loss function of model training in different scenarios.To overcome the update scaling problem,we develop a new boosting strategy by introducing two stealthy metrics.Via experimental results,we show that under both perfect knowledge and limited knowl-edge settings,the multi-party attack is capable of successfully evading detection strategies while guaranteeing the convergence.We also demonstrate that the learned model achieves the high accuracy on the targeted samples,which confirms the significant impact of the multi-party attack on federated learning systems.
