In the ice-covered oceanic region,the collision between sea ice and offshore structures will occur,causing the crushing failure of ice and the vibration of structures.The vibration can result in fatigue damage of stru...In the ice-covered oceanic region,the collision between sea ice and offshore structures will occur,causing the crushing failure of ice and the vibration of structures.The vibration can result in fatigue damage of structure and even endanger the crews’health.It is no doubt that this ice-structure interaction has been noted with great interest by the academic community for a long time and numerous studies have been done through theoretical analysis,experimental statistics and numerical simulation.In this paper,the bond-based Peridynamics method is applied to simulate the interaction between sea ice and wide vertical structures,where sea ice is modeled as elastic-plastic material,with a certain yield condition and failure criterion.Oscillation equation of single-degree-of-freedom is considered to investigate the vibration features of the structure during the interaction process.The damage of ice,ice forces and vibration responses of structure in the duration are obtained through numerical simulation.A parametric investigation is undertaken to identify the key parameters,such as ice thickness,the diameter of structure and relative velocity that trigger the ice crushing,ice forces and vibration responses of the structure.Results indicate that all three parameters have a positive correlation with the overall level of ice force and vibration displacement.Besides,a velocity coefficient is proposed to predict the vibration displacement based on its relation with ice speed.展开更多
Recently,studies show that deep learning-based automatic speech recognition(ASR)systems are vulnerable to adversarial examples(AEs),which add a small amount of noise to the original audio examples.These AE attacks pos...Recently,studies show that deep learning-based automatic speech recognition(ASR)systems are vulnerable to adversarial examples(AEs),which add a small amount of noise to the original audio examples.These AE attacks pose new challenges to deep learning security and have raised significant concerns about deploying ASR systems and devices.The existing defense methods are either limited in application or only defend on results,but not on process.In this work,we propose a novel method to infer the adversary intent and discover audio adversarial examples based on the AEs generation process.The insight of this method is based on the observation:many existing audio AE attacks utilize query-based methods,which means the adversary must send continuous and similar queries to target ASR models during the audio AE generation process.Inspired by this observation,We propose a memory mechanism by adopting audio fingerprint technology to analyze the similarity of the current query with a certain length of memory query.Thus,we can identify when a sequence of queries appears to be suspectable to generate audio AEs.Through extensive evaluation on four state-of-the-art audio AE attacks,we demonstrate that on average our defense identify the adversary’s intent with over 90%accuracy.With careful regard for robustness evaluations,we also analyze our proposed defense and its strength to withstand two adaptive attacks.Finally,our scheme is available out-of-the-box and directly compatible with any ensemble of ASR defense models to uncover audio AE attacks effectively without model retraining.展开更多
Resistive Random-Access Memory(ReRAM)based Processing-in-Memory(PIM)frameworks are proposed to accelerate the working process of DNN models by eliminating the data movement between the computing and memory units.To fu...Resistive Random-Access Memory(ReRAM)based Processing-in-Memory(PIM)frameworks are proposed to accelerate the working process of DNN models by eliminating the data movement between the computing and memory units.To further mitigate the space and energy consumption,DNN model weight sparsity and weight pattern repetition are exploited to optimize these ReRAM-based accelerators.However,most of these works only focus on one aspect of this software/hardware codesign framework and optimize them individually,which makes the design far from optimal.In this paper,we propose PRAP-PIM,which jointly exploits the weight sparsity and weight pattern repetition by using a weight pattern reusing aware pruning method.By relaxing the weight pattern reusing precondition,we propose a similarity-based weight pattern reusing method that can achieve a higher weight pattern reusing ratio.Experimental results show that PRAP-PIM achieves 1.64×performance improvement and 1.51×energy efficiency improvement in popular deep learning benchmarks,compared with the state-of-the-art ReRAM-based DNN accelerators.展开更多
基金This work is supported financially by the National Key R&D Program of China[2018YFC1406000,2016YFE0202700]Supported by the National Natural Science Foundation of China(NSFC)[Grant Nos.51809061,51639004]+1 种基金Supported by the Natural Science Foundation of Heilongjiang Province of China[LC2018021]Supported by the Fundamental Research Funds for the Central Universities[HEUCFM180111].
文摘In the ice-covered oceanic region,the collision between sea ice and offshore structures will occur,causing the crushing failure of ice and the vibration of structures.The vibration can result in fatigue damage of structure and even endanger the crews’health.It is no doubt that this ice-structure interaction has been noted with great interest by the academic community for a long time and numerous studies have been done through theoretical analysis,experimental statistics and numerical simulation.In this paper,the bond-based Peridynamics method is applied to simulate the interaction between sea ice and wide vertical structures,where sea ice is modeled as elastic-plastic material,with a certain yield condition and failure criterion.Oscillation equation of single-degree-of-freedom is considered to investigate the vibration features of the structure during the interaction process.The damage of ice,ice forces and vibration responses of structure in the duration are obtained through numerical simulation.A parametric investigation is undertaken to identify the key parameters,such as ice thickness,the diameter of structure and relative velocity that trigger the ice crushing,ice forces and vibration responses of the structure.Results indicate that all three parameters have a positive correlation with the overall level of ice force and vibration displacement.Besides,a velocity coefficient is proposed to predict the vibration displacement based on its relation with ice speed.
基金supported in part by NSFC No.62202275,Shandong-SF No.ZR2022QF012 projects.
文摘Recently,studies show that deep learning-based automatic speech recognition(ASR)systems are vulnerable to adversarial examples(AEs),which add a small amount of noise to the original audio examples.These AE attacks pose new challenges to deep learning security and have raised significant concerns about deploying ASR systems and devices.The existing defense methods are either limited in application or only defend on results,but not on process.In this work,we propose a novel method to infer the adversary intent and discover audio adversarial examples based on the AEs generation process.The insight of this method is based on the observation:many existing audio AE attacks utilize query-based methods,which means the adversary must send continuous and similar queries to target ASR models during the audio AE generation process.Inspired by this observation,We propose a memory mechanism by adopting audio fingerprint technology to analyze the similarity of the current query with a certain length of memory query.Thus,we can identify when a sequence of queries appears to be suspectable to generate audio AEs.Through extensive evaluation on four state-of-the-art audio AE attacks,we demonstrate that on average our defense identify the adversary’s intent with over 90%accuracy.With careful regard for robustness evaluations,we also analyze our proposed defense and its strength to withstand two adaptive attacks.Finally,our scheme is available out-of-the-box and directly compatible with any ensemble of ASR defense models to uncover audio AE attacks effectively without model retraining.
基金partially supported by the National Natural Science Foundation of China(92064008)the CCF-Huawei Huyanglin Project CCF-HuaweiST2021002+1 种基金the Open Project Program of Wuhan National Laboratory for Optoelectronics(2022WNLOKF018)the Shandong Provincial Natural Science Foundation(ZR2022LZH010).
文摘Resistive Random-Access Memory(ReRAM)based Processing-in-Memory(PIM)frameworks are proposed to accelerate the working process of DNN models by eliminating the data movement between the computing and memory units.To further mitigate the space and energy consumption,DNN model weight sparsity and weight pattern repetition are exploited to optimize these ReRAM-based accelerators.However,most of these works only focus on one aspect of this software/hardware codesign framework and optimize them individually,which makes the design far from optimal.In this paper,we propose PRAP-PIM,which jointly exploits the weight sparsity and weight pattern repetition by using a weight pattern reusing aware pruning method.By relaxing the weight pattern reusing precondition,we propose a similarity-based weight pattern reusing method that can achieve a higher weight pattern reusing ratio.Experimental results show that PRAP-PIM achieves 1.64×performance improvement and 1.51×energy efficiency improvement in popular deep learning benchmarks,compared with the state-of-the-art ReRAM-based DNN accelerators.