SafeDeep: A Scalable Robustness Verification Framework for Deep Neural Networks
(2023) IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023- Abstract
- The state-of-the-art machine learning techniques come with limited, if at all any, formal correctness guarantees. This has been demonstrated by adversarial examples in the deep learning domain. To address this challenge, here, we propose a scalable robustness verification framework for Deep Neural Networks (DNNs). The framework relies on Linear Programming (LP) engines and builds on decades of advances in the field for analyzing convex approximations of the original network. The key insight is in the on-demand incremental refinement of these convex approximations. This refinement can be parallelized, making the framework even more scalable. We have implemented a prototype tool to verify the robustness of a large number of DNNs in epileptic... (More)
- The state-of-the-art machine learning techniques come with limited, if at all any, formal correctness guarantees. This has been demonstrated by adversarial examples in the deep learning domain. To address this challenge, here, we propose a scalable robustness verification framework for Deep Neural Networks (DNNs). The framework relies on Linear Programming (LP) engines and builds on decades of advances in the field for analyzing convex approximations of the original network. The key insight is in the on-demand incremental refinement of these convex approximations. This refinement can be parallelized, making the framework even more scalable. We have implemented a prototype tool to verify the robustness of a large number of DNNs in epileptic seizure detection. We have compared the results with those obtained by two state-of-the-art tools for the verification of DNNs. We show that our framework is consistently more precise than the over-approximation-based tool ERAN and more scalable than the SMT-based tool Reluplex. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7c504e0f-72f6-4f87-961f-453803f3dd7c
- author
- Baninajjar, Anahita LU ; Hosseini, Kamran ; Rezine, Ahmed and Aminifar, Amir LU
- organization
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- in press
- subject
- host publication
- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing
- conference name
- IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023
- conference location
- Rhodes Island, Greece
- conference dates
- 2023-06-04 - 2023-06-10
- external identifiers
-
- scopus:85180553668
- DOI
- 10.1109/ICASSP49357.2023.10097028
- project
- WASP: Wallenberg AI, Autonomous Systems and Software Program at Lund University
- language
- English
- LU publication?
- yes
- id
- 7c504e0f-72f6-4f87-961f-453803f3dd7c
- date added to LUP
- 2023-03-30 15:23:35
- date last changed
- 2024-02-08 15:38:59
@inproceedings{7c504e0f-72f6-4f87-961f-453803f3dd7c, abstract = {{The state-of-the-art machine learning techniques come with limited, if at all any, formal correctness guarantees. This has been demonstrated by adversarial examples in the deep learning domain. To address this challenge, here, we propose a scalable robustness verification framework for Deep Neural Networks (DNNs). The framework relies on Linear Programming (LP) engines and builds on decades of advances in the field for analyzing convex approximations of the original network. The key insight is in the on-demand incremental refinement of these convex approximations. This refinement can be parallelized, making the framework even more scalable. We have implemented a prototype tool to verify the robustness of a large number of DNNs in epileptic seizure detection. We have compared the results with those obtained by two state-of-the-art tools for the verification of DNNs. We show that our framework is consistently more precise than the over-approximation-based tool ERAN and more scalable than the SMT-based tool Reluplex.}}, author = {{Baninajjar, Anahita and Hosseini, Kamran and Rezine, Ahmed and Aminifar, Amir}}, booktitle = {{2023 IEEE International Conference on Acoustics, Speech and Signal Processing}}, language = {{eng}}, title = {{SafeDeep: A Scalable Robustness Verification Framework for Deep Neural Networks}}, url = {{https://lup.lub.lu.se/search/files/141851887/SafeDeep.pdf}}, doi = {{10.1109/ICASSP49357.2023.10097028}}, year = {{2023}}, }