Name
Title | ||
|---|---|---|
Property-Directed Verification and Robustness Certification of Recurrent Neural Networks |
Abstract | ||
|---|---|---|
This paper presents a property-directed approach to verifying recurrent neural networks (RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a given RNN using active automata learning. This model may then be analyzed using model checking as a verification technique. The term property-directed reflects the idea that our procedure is guided and controlled by the given property rather than performing the two steps separately. We show that this not only allows us to discover small counterexamples fast, but also to generalize them by pumping towards faulty flows hinting at the underlying error in the RNN. We also show that our method can be efficiently used for adversarial robustness certification of RNNs. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1007/978-3-030-88885-5_24 | AUTOMATED TECHNOLOGY FOR VERIFICATION AND ANALYSIS, ATVA 2021 |
DocType | Volume | ISSN |
Conference | 12971 | 0302-9743 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
10 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Igor Khmelnitsky | 1 | 0 | 1.01 |
| Daniel Neider | 2 | 1 | 0.70 |
| Roy Rajarshi | 3 | 2 | 0.73 |
| Xuan Xie | 4 | 11 | 7.24 |
| Benoît Barbot | 5 | 0 | 0.34 |
| Benedikt Bollig | 6 | 0 | 0.34 |
| Alain Finkel | 7 | 0 | 0.34 |
| Serge Haddad | 8 | 0 | 0.34 |
| Martin Leucker | 9 | 1639 | 112.68 |
| Lina Ye | 10 | 26 | 8.75 |