Verifying Neural Networks Against Backdoor Attacks

DOI10.1007/978-3-031-13185-1_9MaRDI QIDQ6487317zbMATH OpenFDO

Authors Long H. Pham, Jun Sun

Publication date 7 December 2022

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/978-3-031-13185-1_9

Mathematics Subject Classification ID

Specification and verification (program logics, model checking, etc.) (68Q60) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Exploiting verified neural networks via floating point numerical error
• Detecting scene-plausible perceptible backdoors in trained DNNs without access to the training set
• Shared Certificates for Neural Network Verification
• An SMT-based approach for verifying binarized neural networks
• Safety verification of deep neural networks

Cites work

• Formal verification of piece-wise linear feed-forward neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Safety verification of deep neural networks

Cited in

(1)

• Detecting scene-plausible perceptible backdoors in trained DNNs without access to the training set

This page was built for publication: Verifying Neural Networks Against Backdoor Attacks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6487317)