Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents.However,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experi...Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents.However,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experiences that hinder convergence,resulting in ineffective training performance for multi‐agent systems.To tackle this issue,a novel reinforcement learning scheme,Mutual Information Oriented Deep Skill Chaining(MioDSC),is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency.These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state.In addition,MioDSC can generate cooperative policies using the options framework,allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent learning.MioDSC was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty levels.The experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.展开更多
To cope with privacy leakage caused by multimedia outsourcing and sharing,data provenance is used to analyze leaked multimedia and provide reactive accountability.Existing schemes of multimedia provenance are based on...To cope with privacy leakage caused by multimedia outsourcing and sharing,data provenance is used to analyze leaked multimedia and provide reactive accountability.Existing schemes of multimedia provenance are based on watermarking protocols.In an outsourcing scenario,existing schemes face two severe challenges:1)when data leakage occurs,there exists a probability that data provenance results can be repudiated,in which case data provenance tracking fails;and 2)when outsourced data are shared,data encryption transfer causes key management burden outside the schemes,and privacy leakage threatens users.In this paper,we propose a novel data provenance scheme with an improved LUT-based fingerprinting protocol,which integrates an asymmetric watermarking protocol,robust watermark algorithm and homomorphic encryption and digital signatures to achieve full non-repudiation provenance.We build an in-scheme stream cipher to protect outsourced multimedia data from privacy leakage and complicated key management.Our scheme is also lightweight and easy to deploy.Extensive security and performance analysis compares our scheme with the state of the art.The results show that our scheme has not only better provenance security and data confidentiality but also higher efficiency for multimedia outsourcing,sharing and provenance.展开更多
Interact traffic classification is vital to the areas of network operation and management. Traditional classification methods such as port mapping and payload analysis are becoming increasingly difficult as newly emer...Interact traffic classification is vital to the areas of network operation and management. Traditional classification methods such as port mapping and payload analysis are becoming increasingly difficult as newly emerged applications （e. g. Peer-to-Peer） using dynamic port numbers, masquerading techniques and encryption to avoid detection. This paper presents a machine learning （ML） based traffic classifica- tion scheme, which offers solutions to a variety of network activities and provides a platform of performance evaluation for the classifiers. The impact of dataset size, feature selection, number of application types and ML algorithm selection on classification performance is analyzed and demonstrated by the following experiments： （1） The genetic algorithm based feature selection can dramatically reduce the cost without diminishing classification accuracy. （2） The chosen ML algorithms can achieve high classification accuracy. Particularly, REPTree and C4.5 outperform the other ML algorithms when computational complexity and accuracy are both taken into account. （3） Larger dataset and fewer application types would result in better classification accuracy. Finally, early detection with only several initial packets is proposed for real-time network activity and it is proved to be feasible according to the preliminary results.展开更多
基金National Natural Science Foundation of China,Grant/Award Number:61872171The Belt and Road Special Foundation of the State Key Laboratory of Hydrology‐Water Resources and Hydraulic Engineering,Grant/Award Number:2021490811。
文摘Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual agents.However,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experiences that hinder convergence,resulting in ineffective training performance for multi‐agent systems.To tackle this issue,a novel reinforcement learning scheme,Mutual Information Oriented Deep Skill Chaining(MioDSC),is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency.These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state.In addition,MioDSC can generate cooperative policies using the options framework,allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent learning.MioDSC was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty levels.The experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.
基金The authors would like to thank the anonymous referees for their valuable comments and helpful suggestions.The work is supported by the National Key Research and Development Program of China(No.2016YFB0800402)the National Natural Science Foundation of China(No.U1405254,No.U1536207).
文摘To cope with privacy leakage caused by multimedia outsourcing and sharing,data provenance is used to analyze leaked multimedia and provide reactive accountability.Existing schemes of multimedia provenance are based on watermarking protocols.In an outsourcing scenario,existing schemes face two severe challenges:1)when data leakage occurs,there exists a probability that data provenance results can be repudiated,in which case data provenance tracking fails;and 2)when outsourced data are shared,data encryption transfer causes key management burden outside the schemes,and privacy leakage threatens users.In this paper,we propose a novel data provenance scheme with an improved LUT-based fingerprinting protocol,which integrates an asymmetric watermarking protocol,robust watermark algorithm and homomorphic encryption and digital signatures to achieve full non-repudiation provenance.We build an in-scheme stream cipher to protect outsourced multimedia data from privacy leakage and complicated key management.Our scheme is also lightweight and easy to deploy.Extensive security and performance analysis compares our scheme with the state of the art.The results show that our scheme has not only better provenance security and data confidentiality but also higher efficiency for multimedia outsourcing,sharing and provenance.
基金Supported by the National High Technology Research and Development Programme of China (No. 2005AA121620, 2006AA01Z232)the Zhejiang Provincial Natural Science Foundation of China (No. Y1080935 )the Research Innovation Program for Graduate Students in Jiangsu Province (No. CX07B_ 110zF)
文摘Interact traffic classification is vital to the areas of network operation and management. Traditional classification methods such as port mapping and payload analysis are becoming increasingly difficult as newly emerged applications （e. g. Peer-to-Peer） using dynamic port numbers, masquerading techniques and encryption to avoid detection. This paper presents a machine learning （ML） based traffic classifica- tion scheme, which offers solutions to a variety of network activities and provides a platform of performance evaluation for the classifiers. The impact of dataset size, feature selection, number of application types and ML algorithm selection on classification performance is analyzed and demonstrated by the following experiments： （1） The genetic algorithm based feature selection can dramatically reduce the cost without diminishing classification accuracy. （2） The chosen ML algorithms can achieve high classification accuracy. Particularly, REPTree and C4.5 outperform the other ML algorithms when computational complexity and accuracy are both taken into account. （3） Larger dataset and fewer application types would result in better classification accuracy. Finally, early detection with only several initial packets is proposed for real-time network activity and it is proved to be feasible according to the preliminary results.
