Pupil dynamics are the important characteristics of face spoofing detection.The face recognition system is one of the most used biometrics for authenticating individual identity.The main threats to the facial recognit...Pupil dynamics are the important characteristics of face spoofing detection.The face recognition system is one of the most used biometrics for authenticating individual identity.The main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,etc.The proposed model uses pupil characteristics for liveness detection during the authentication process.The pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light intensities.The proposed framework consists of two-phase methodologies.In the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video frames.The above measurement is converted into feature space using Kohn and Clynes model-defined parameters.The Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the camera.In the second phase,we perform the facial recognition process.Scale-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional vector.These features are scale,rotation,and orientation invariant and are used for recognizing facial images.The brute force matching algorithm is used for matching features of two different images.The threshold value we considered is 0.08 for good matches.To analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Error Rate,while the Replay Attack datasets showed a 92.1%Equal Error Rate.展开更多
Phototropism is a classic adaptive growth response that helps plants to enhance light capture for photosynthesis.It was shown that hydrogen peroxide(H_(2)O_(2))participates in the regulation of blue light-induced hypo...Phototropism is a classic adaptive growth response that helps plants to enhance light capture for photosynthesis.It was shown that hydrogen peroxide(H_(2)O_(2))participates in the regulation of blue light-induced hypocotyl phototropism;however,the underlying mechanism is unclear.In this study,we demonstrate that the unilateral high-intensity blue light(HBL)could induce asymmetric distribution of H_(2)O_(2) in cotton hypocotyls.Disruption of the HBL-induced asymmetric distribution of H_(2)O_(2) by applying either H_(2)O_(2) itself evenly on the hypocotyls or H_(2)O_(2) scavengers on the lit side of hypocotyls could efficiently inhibit hypocotyl phototropic growth.Consistently,application of H_(2)O_(2) on the shaded and lit sides of the hypocotyls led to reduced and enhanced hypocotyl phototropism,respectively.Further,we show that H_(2)O_(2) inhibits hypocotyl elongation of cotton seedlings,thus supporting the repressive role of H_(2)O_(2) in HBL-induced hypocotyl phototropism.Moreover,our results show that H_(2)O_(2) interferes with HBL-induced asymmetric distribution of auxin in the cotton hypocotyls.Taken together,our study uncovers that H_(2)O_(2) changes the asymmetric accumulation of auxin and inhibits hypocotyl cell elongation,thus mediating HBL-induced hypocotyl phototropism.展开更多
分布式拒绝服务(DDoS)攻击一直是互联网的主要威胁之一,在软件定义网络(SDN)中会导致控制器资源耗尽,影响整个网络正常运行。针对SDN网络中的DDoS攻击问题,文章设计并实现了一种两级攻击检测与防御方法。基于控制器北向接口采集交换机...分布式拒绝服务(DDoS)攻击一直是互联网的主要威胁之一,在软件定义网络(SDN)中会导致控制器资源耗尽,影响整个网络正常运行。针对SDN网络中的DDoS攻击问题,文章设计并实现了一种两级攻击检测与防御方法。基于控制器北向接口采集交换机流表数据并提取直接特征和派生特征,采用序贯概率比检验(Sequential Probability Ratio Test,SPRT)和轻量级梯度提升机(LightGBM)设计两级攻击检测算法,快速定位攻击端口和对攻击类型进行精准划分,通过下发流表规则对攻击流量进行实时过滤。实验结果表明,攻击检测模块能够快速定位攻击端口并对攻击类型进行精准划分,分类准确率达到98%,攻击防御模块能够在攻击发生后2 s内迅速下发防御规则,对攻击流量进行过滤,有效保护SDN网络的安全。展开更多
基金funded by Researchers Supporting Program at King Saud University (RSPD2023R809).
文摘Pupil dynamics are the important characteristics of face spoofing detection.The face recognition system is one of the most used biometrics for authenticating individual identity.The main threats to the facial recognition system are different types of presentation attacks like print attacks,3D mask attacks,replay attacks,etc.The proposed model uses pupil characteristics for liveness detection during the authentication process.The pupillary light reflex is an involuntary reaction controlling the pupil’s diameter at different light intensities.The proposed framework consists of two-phase methodologies.In the first phase,the pupil’s diameter is calculated by applying stimulus(light)in one eye of the subject and calculating the constriction of the pupil size on both eyes in different video frames.The above measurement is converted into feature space using Kohn and Clynes model-defined parameters.The Support Vector Machine is used to classify legitimate subjects when the diameter change is normal(or when the eye is alive)or illegitimate subjects when there is no change or abnormal oscillations of pupil behavior due to the presence of printed photograph,video,or 3D mask of the subject in front of the camera.In the second phase,we perform the facial recognition process.Scale-invariant feature transform(SIFT)is used to find the features from the facial images,with each feature having a size of a 128-dimensional vector.These features are scale,rotation,and orientation invariant and are used for recognizing facial images.The brute force matching algorithm is used for matching features of two different images.The threshold value we considered is 0.08 for good matches.To analyze the performance of the framework,we tested our model in two Face antispoofing datasets named Replay attack datasets and CASIA-SURF datasets,which were used because they contain the videos of the subjects in each sample having three modalities(RGB,IR,Depth).The CASIA-SURF datasets showed an 89.9%Equal Error Rate,while the Replay Attack datasets showed a 92.1%Equal Error Rate.
基金the financial support from the National Natural Science Foundation of China(Grant nos.32100225,32200252,31871419)the Natural Science Foundation of Henan province(grant nos.212300410214)Central Plain Talent Scheme(Grants.ZYYCYU202012164).
文摘Phototropism is a classic adaptive growth response that helps plants to enhance light capture for photosynthesis.It was shown that hydrogen peroxide(H_(2)O_(2))participates in the regulation of blue light-induced hypocotyl phototropism;however,the underlying mechanism is unclear.In this study,we demonstrate that the unilateral high-intensity blue light(HBL)could induce asymmetric distribution of H_(2)O_(2) in cotton hypocotyls.Disruption of the HBL-induced asymmetric distribution of H_(2)O_(2) by applying either H_(2)O_(2) itself evenly on the hypocotyls or H_(2)O_(2) scavengers on the lit side of hypocotyls could efficiently inhibit hypocotyl phototropic growth.Consistently,application of H_(2)O_(2) on the shaded and lit sides of the hypocotyls led to reduced and enhanced hypocotyl phototropism,respectively.Further,we show that H_(2)O_(2) inhibits hypocotyl elongation of cotton seedlings,thus supporting the repressive role of H_(2)O_(2) in HBL-induced hypocotyl phototropism.Moreover,our results show that H_(2)O_(2) interferes with HBL-induced asymmetric distribution of auxin in the cotton hypocotyls.Taken together,our study uncovers that H_(2)O_(2) changes the asymmetric accumulation of auxin and inhibits hypocotyl cell elongation,thus mediating HBL-induced hypocotyl phototropism.
文摘分布式拒绝服务(DDoS)攻击一直是互联网的主要威胁之一,在软件定义网络(SDN)中会导致控制器资源耗尽,影响整个网络正常运行。针对SDN网络中的DDoS攻击问题,文章设计并实现了一种两级攻击检测与防御方法。基于控制器北向接口采集交换机流表数据并提取直接特征和派生特征,采用序贯概率比检验(Sequential Probability Ratio Test,SPRT)和轻量级梯度提升机(LightGBM)设计两级攻击检测算法,快速定位攻击端口和对攻击类型进行精准划分,通过下发流表规则对攻击流量进行实时过滤。实验结果表明,攻击检测模块能够快速定位攻击端口并对攻击类型进行精准划分,分类准确率达到98%,攻击防御模块能够在攻击发生后2 s内迅速下发防御规则,对攻击流量进行过滤,有效保护SDN网络的安全。
