Relational DNN Verification With Cross Executional Bound Refinement
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914798913978368 |
|---|---|
| author | Banerjee, Debangshu Singh, Gagandeep |
| author_facet | Banerjee, Debangshu Singh, Gagandeep |
| contents | We focus on verifying relational properties defined over deep neural networks (DNNs) such as robustness against universal adversarial perturbations (UAP), certified worst-case hamming distance for binary string classifications, etc. Precise verification of these properties requires reasoning about multiple executions of the same DNN. However, most of the existing works in DNN verification only handle properties defined over single executions and as a result, are imprecise for relational properties. Though few recent works for relational DNN verification, capture linear dependencies between the inputs of multiple executions, they do not leverage dependencies between the outputs of hidden layers producing imprecise results. We develop a scalable relational verifier RACoon that utilizes cross-execution dependencies at all layers of the DNN gaining substantial precision over SOTA baselines on a wide range of datasets, networks, and relational properties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10143 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Relational DNN Verification With Cross Executional Bound Refinement Banerjee, Debangshu Singh, Gagandeep Machine Learning We focus on verifying relational properties defined over deep neural networks (DNNs) such as robustness against universal adversarial perturbations (UAP), certified worst-case hamming distance for binary string classifications, etc. Precise verification of these properties requires reasoning about multiple executions of the same DNN. However, most of the existing works in DNN verification only handle properties defined over single executions and as a result, are imprecise for relational properties. Though few recent works for relational DNN verification, capture linear dependencies between the inputs of multiple executions, they do not leverage dependencies between the outputs of hidden layers producing imprecise results. We develop a scalable relational verifier RACoon that utilizes cross-execution dependencies at all layers of the DNN gaining substantial precision over SOTA baselines on a wide range of datasets, networks, and relational properties. |
| title | Relational DNN Verification With Cross Executional Bound Refinement |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.10143 |