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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Scopus citations

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. In this paper, we present Cert-RNN, a general framework for certifying the robustness of RNNs. Specifically, through detailed analysis for the intrinsic property of the unique function in different ranges, we exhaustively discuss different cases for the exact formula of bounding planes, based on which we design several precise and efficient abstract transformers for the unique calculations in RNNs. Cert-RNN significantly outperforms the state-of-the-art methods (e.g., POPQORN) in terms of (i) effectiveness - it provides much tighter robustness bounds, and (ii) efficiency - it scales to much more complex models. Through extensive evaluation, we validate Cert-RNN's superior performance across various network architectures (e.g., vanilla RNN and LSTM) and applications (e.g., image classification, sentiment analysis, toxic comment detection, and malicious URL detection). For instance, for the RNN-2-32 model on the MNIST sequence dataset, the robustness bound certified by Cert-RNN is on average 1.86 times larger than that by POPQORN. Besides certifying the robustness of given RNNs, Cert-RNN also enables a range of practical applications including evaluating the provable effectiveness for various defenses (i.e., the defense with a larger robustness region is considered to be more robust), improving the robustness of RNNs (i.e., incorporating Cert-RNN with verified robust training) and identifying sensitive words (i.e., the word with the smallest certified robustness bound is considered to be the most sensitive word in a sentence), which helps build more robust and interpretable deep learning systems. We will open-source Cert-RNN for facilitating the DNN security research.

Original languageEnglish (US)
Title of host publicationCCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
PublisherAssociation for Computing Machinery
Pages516-534
Number of pages19
ISBN (Electronic)9781450384544
DOIs
StatePublished - Nov 12 2021
Event27th ACM Annual Conference on Computer and Communication Security, CCS 2021 - Virtual, Online, Korea, Republic of
Duration: Nov 15 2021Nov 19 2021

Publication series

NameProceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)1543-7221

Conference

Conference27th ACM Annual Conference on Computer and Communication Security, CCS 2021
Country/TerritoryKorea, Republic of
CityVirtual, Online
Period11/15/2111/19/21

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this