Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networks
Tianyu Du, Shouling Ji, Lujia Shen, Yao Zhang, Jinfeng Li, Jie Shi, Chengfang Fang, Jianwei Yin, Raheem Beyah, Ting Wang
Abstract
Certifiable robustness, the functionality of verifying whether the given region surrounding a data point admits any adversarial example, provides guaranteed security for neural networks deployed in adversarial environments. A plethora of work has been proposed to certify the robustness of feed-forward networks, e.g., FCNs and CNNs. Yet, most existing methods cannot be directly applied to recurrent neural networks (RNNs), due to their sequential inputs and unique operations.
Topics & Concepts
Robustness (evolution)Recurrent neural networkComputer scienceAdversarial systemArtificial neural networkArtificial intelligenceMachine learningDeep neural networksGeneChemistryBiochemistryAdversarial Robustness in Machine LearningSecurity and Verification in ComputingPhysical Unclonable Functions (PUFs) and Hardware Security